检索结果-内蒙古大学图书馆

Multiple object tracking based on appearance and motion graph convolutional neural networks with an explainer

Neural Computing and Applications 2024年第22期36卷 13799-13814页

作者： Zhang, Yubo Huang, Qingming Zheng, Liying School of Computer Science and Technology Harbin Engineering University 145 Nantong Street Heilongjiang Harbin150001 China School of Computer Science and Technology University of Chinese Academy of Sciences Huairou District Beijing100019 China

The tracking performance of Multi-Object Tracking (MOT) has recently been improved by using discriminative appearance and motion features. However, dense crowds and occlusions significantly reduce the reliability of these features, resulting in unsatisfied tracking performance. Thus, we design an end-to-end MOT model based on Graph Convolutional Neural Networks (GCNNs) which fuses four classes of features that characterize objects from their appearances, motions, appearance interactions, and motion interactions. Specifically, a Re-Identification (Re-ID) module is used to extract more discriminative appearance features. The appearance features from object tracklets are then averaged to simplify the proposed tracker. Then, we design two GCNNs to better distinguish objects. One is for extracting interactive appearance features, and the other is for interactive motion features. A fusion module then fuses those features, getting the global feature similarity based on which an association component calculates the MOT matching results. Finally, we semantically visualize relevant structures with the GNNExplainer for insight into the proposed tracker. The evaluation results on MOT16 and MOT17 benchmarks show that our model outperforms the state-of-the-art online tracking methods in terms of Multi-Object Tracking Accuracy and Identification F1 score which is consistent with the results from the GNNExplainer. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Unleashing the power of pseudo-code for binary code similarity analysis

引用

Cybersecurity 2023年第2期6卷 44-61页

作者： Weiwei Zhang Zhengzi Xu Yang Xiao Yinxing Xue School of Computer Science and Engineering University of Science and Technology of ChinaHefeiChina School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Institute of Information Engineering Chinese Academy of SciencesBeijingChina School of Cyber Security University of Chinese Academy of SciencesBeijingChina

Code similarity analysis has become more popular due to its significant applicantions,including vulnerability detection,malware detection,and patch *** the source code of the software is difficult to obtain under most circumstances,binary-level code similarity analysis(BCSA)has been paid much attention *** recent years,many BCSA studies incorporating Al techniques focus on deriving semantic information from binary functions with code representations such as assembly code,intermediate representations,and control flow graphs to measure the ***,due to the impacts of different compilers,architectures,and obfuscations,binaries compiled from the same source code may vary considerably,which becomes the major obstacle for these works to obtain robust *** this paper,we propose a solution,named UPPC(Unleashing the Power of Pseudo-code),which leverages the pseudo-code of binary function as input,to address the binary code similarity analysis challenge,since pseudocode has higher abstraction and is platform-independent compared to binary *** selectively inlines the functions to capture the full function semantics across different compiler optimization levels and uses a deep pyramidal convolutional neural network to obtain the semantic embedding of the *** evaluated UPPC on a data set containing vulnerabilities and a data set including different architectures(X86,ARM),different optimization options(O0-O3),different compilers(GCC,Clang),and four obfuscation *** experimental results show that the accuracy of UPPC in function search is 33.2%higher than that of existing methods.

关键词： Binary code similarity Machine learning Software security Pseudo-code

来源：评论

学校读者我要写书评

暂无评论

Smart automated highway lighting system using IoT: a survey

引用

Energy Informatics 2024年第1期7卷 76页

作者： Achar, Tejaswini Eshwar Rekha, C. Shreyas, J. Department of Computer Science and Engineering Government Engineering College Koppal Talakal India Department of Information Science and Engineering Bapuji Institute of Engineering and Technology Davanagere India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

Efficient highway lighting is crucial for ensuring road safety and reducing energy consumption and costs. Traditional highway lighting systems rely on timers or simple photosensors, leading to inefficient operation by illuminating lights when not needed or failing to adjust to changing conditions. The emergence of the Internet of Things (IoT) and related technologies has enabled the development of smart automated highway lighting systems that can dynamically control illumination levels based on real-time data. This paper provides a comprehensive review of the current state-of-the-art in smart automated highway lighting systems employing IoT technologies. Key components, communication protocols, data processing techniques, and lighting control strategies are discussed. The integration of renewable energy sources and energy storage systems is explored for environmentally sustainable operations. Practical implementation case studies are analyzed to highlight benefits and challenges. Open research issues and future directions for further enhancements are identified. © The Author(s) 2024.

关键词： Street lighting

来源：评论

学校读者我要写书评

暂无评论

An autoencoder based unsupervised clustering approach to analyze the effect of E-learning on the mental health of Indian students during the Covid-19 pandemic

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Banerjee, Pritha Jana, Chandan Saha, Jayita Chowdhury, Chandreyee Computer Application and Science Institute of Engineering and Management West Bengal Kolkata700091 India Computer Science and Engineering Jadavpur University West Bengal Kolkata700032 India Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal Karnataka Bengaluru560064 India

Due to the Covid-19 pandemic, the education system in India has changed to remote that is, online study mode. Though there are works on the effect of teaching learning on Indian students, the effect of online mode and associated mental state, particularly when the entire country is going through a crisis could not be found in the literature. Our goal is to analyze data and find some pattern through which we can understand the effectiveness of the online study and also try to figure out the stress level. The dataset we collected from 500 undergraduate college students during April-May, 2021 is in questionnaire format. Our contribution in this paper are - (i) publishing a dataset of student feedbacks, and (ii) designing a data processing pipeline involving autoencoders followed by clustering approach. The dataset is in text format so for our analysis we have converted the dataset into a numerical format using the concept of a binary bag of words. Dimensionality reduction is applied through autoencoder for an effective latent space representation. Finally, for finding patterns out of this dimensionally reduced feature space, we have applied unsupervised learning algorithms - kMeans and DBSCAN. A thorough analysis of the clustering process reveals that the absence of social communication in purely online education provokes isolation irrespective of the urban or rural background of the students. However, it could supplement offline classes as a substantial number of students welcomed the concept of online learning as reported in the data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast Cancer Using Computational Machine Learning Algorithms 8th

Classification of Breast Cancer Using Computational Machine ...

引用

8th International Conference on Emerging Research in Computing, Information, Communication and Applications, ERCICA 2023

作者： Gagana, P. Aladakatti, Darshan Kodipalli, Ashwini Rao, Trupthi Kamal, Shoaib Electronics and Communication Engineering Global Academy of Technology Bangalore India Computer Science and Engineering Global Academy of Technology Bangalore India Artificial Intelligence and Data Science Engineering Global Academy of Technology Bangalore India

ISBN: (纸本)9789819976324

Cancer is a disease that brings fear in everyone’s heart. In the top 5 cancers listed by Stephanie Watson and reviewed by Medically Reviewed by Jennifer Robinson, says that breast cancer stands in the top third position among other dreadful cancers like Prostate Cancer, Pancreatic Cancer, Colorectal Cancer, and Lung Cancer. Numerous kinds of research are made on this terrifying disease yet millions and millions of women have lost their precious life due to breast cancer. A huge number of patients have been victimized by this curse on women. In severe cases, doctors fail to give hope and treatment as the patient’s conditions reach beyond medical help. We all have heard the quote "Prevention is better than cure", well in our case earlier detection is better than late realization. As earlier as modern-day treatments are based on the concept of molecular heterogeneity, which is why they can be influenced by various features. Early breast cancer, usually confined to the breast, is considered a curable disease. This stage is commonly known as benign, which in our dataset is represented as however when the symptoms are not detected and treated at the early stage the treatment becomes more complicated and cannot to treated using the present therapeutic options and might have an associated risk of spreading to other parts of the body. This condition is called malignant and this is represented as M in the dataset. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Integrated feature selection and ensemble learning for heart disease detection: a 2-tier approach with ALAN and ET-ABDF machine learning model

引用

International Journal of Information technology (Singapore) 2024年第7期16卷 4489-4503页

作者： Mandula, Aruna Vijaya Kumar, Baby Shalini Department of Computer Science and Engineering Kalasalingam Academy of Research Education Department of Information Technology Kalasalingam Academy of Research Education

The findings of this investigation give a novel approach to the forecasting of heart disease. For the purpose of determining significant features, it is a 2-tier procedure that uses a combination of the analysis of variance (ANOVA) and Least Absolute Shrinkage and Selection Operator (lasso) regression known as ALAN. In addition to this, it uses the Ensemble Technique with Adaptive Boosted Decision Fusion (ET-ABDF) in order to enhance its accuracy. An improvement in the detection of critical properties for predictive modelling is achieved through the use of the ALAN technique. With an accuracy of 88.0%, precision of 89.81%, recall of 89.80%, and an F1 Score of 89.00%, the ET-ABDF model shows outstanding results in the identification of cardiac disease. The outstanding result of 96.21% for the area under the curve (AUC) shows its strong ability to differentiate across several groups. It has been established through the comparative analysis that the model that has been provided displays better results in comparison to other algorithms. It is possible that in the future, undertaking more research on new techniques for choosing characteristics and expanding studies to encompass a larger spectrum of cardiovascular problems will have the potential to increase the accuracy and practicability of heart disease prediction models in real-world healthcare settings. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Adaptive Boosted Decision Fusion (ET-ABDF) ALAN ANOVA Lasso regression

来源：评论

学校读者我要写书评

暂无评论

Track correlation algorithm based on CNN-LSTM for swarm targets

引用

Journal of Systems engineering and Electronics 2024年第2期35卷 417-429页

作者： CHEN Jinyang WANG Xuhua CHEN Xian Research Institute for National Defense Engineering Academy of Military SciencesLuoyang 471023China Information Engineering University Zhengzhou 450001China School of Computer Science and Technology Xidian UniversityXi’an 710071China

The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for *** this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm ***, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.

关键词： track correlation correlation accuracy rate swarm target convolutional neural network(CNN) long short-term memory(LSTM)neural network

来源：评论

学校读者我要写书评

暂无评论

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5475-5488页

作者： Wang, Youze Hu, Wenbo Dong, Yinpeng Liu, Jing Zhang, Hanwang Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China Tsinghua University Beijing100084 China Chinese academy of science Institute of automation Beijing100190 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human intelligence, which processes a variety of data forms beyond just text. Despite advancements, the undesirable generation of these models remains a critical concern, particularly due to vulnerabilities exposed by text-based jailbreak attacks, which have represented a significant threat by challenging existing safety protocols. Motivated by the unique security risks posed by the integration of new and old modalities for MLLMs, we propose a unified multimodal universal jailbreak attack framework that leverages iterative image-text interactions and transfer-based strategy to generate a universal adversarial suffix and image. Our work not only highlights the interaction of image-text modalities can be used as a critical vulnerability but also validates that multimodal universal jailbreak attacks can bring higher-quality undesirable generations across different MLLMs. We evaluate the undesirable context generation of MLLMs like LLaVA, Yi-VL, MiniGPT4, MiniGPT-v2, and InstructBLIP, and reveal significant multimodal safety alignment issues, highlighting the inadequacy of current safety mechanisms against sophisticated multimodal attacks. This study underscores the urgent need for robust safety measures in MLLMs, advocating for a comprehensive review and enhancement of security protocols to mitigate potential risks associated with multimodal capabilities. © 1991-2012 IEEE.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

Cross domain recommendation using dual inductive transfer learning

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Zaman, Nilufar Jana, Angshuman Computer Engineering Trinity Academy of Engineering Kondhwa-Saswad Road Maharashtra Pune411048 India Computer Science Indian Institute of Information Technology Guwahati Bongora Assam Guwahati781015 India

Cross Domain Recommendations have made a great impact on the field of online services. It helps the service provider of one domain to understand their users from the information of other domains to recommend the correct product to them. Unlike other traditional approaches, our approach finds both way latent relations between users and items considering the interactions between users and items. Traditional model normally avoids considering any implicit information about the user or item for calculating the latent relation between them. But our model Dual Inductive Transfer Learning(DITL) uses all possible user and item features and the ratings provided for recommendations. Our model learns the user’s preferences across the source and target domain and thus preserves the user’s taste across different but related domains. Our model auto-encodes the features in a feature vector to extract the user’s taste and thus transfers this across domains for efficient recommendation. The proposed model is tested on three huge benchmark datasets, the Douban dataset, the Amazon 5-crore dataset for the domain of movies, books and music whereas Tenrec dataset for the domain of articles and videos and it proves to outperform the classical cross-domain recommendation systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Smartphone based human activity recognition irrespective of usage behavior using deep learning technique

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 69-85页

作者： Kundu, Soumya Mallik, Manjarini Saha, Jayita Chowdhury, Chandreyee Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

Human activity recognition (HAR) from sensory data is a crucial task for a wide variety of applications. The in-built inertial sensor facilities of commercial smartphones have made the data collection process easier. However, different smartphone configurations exhibit variations in sensor readings for the same activities. Different smartphone holding positions, like in hand, shirt, or trouser pockets, also lead to variations in signal patterns for the same activity. Some recent works have shown that automated feature extraction using deep learning methods can significantly improve activity recognition, although there is a lack of experimentation considering device heterogeneity and different smartphone holding positions. The proposed work addresses this research gap with a two-fold contribution. First, a CNN-based HAR framework is proposed that forms 2-D frequency domain images to capture temporal patterns in the data along with inter-axis spatial features. Second, an ensemble of conditional classifiers has been designed based on CNN that exhibits generality in terms of device configurations and usage behavior. Real life data have been collected for different activities using different devices for experimentation. The proposed ensemble model is found to recognize activities with 94% accuracy even when the training and test devices are different for real datasets. © The Author(s) 2024.

关键词： Activity image CNN Deep learning Human activity recognition Smartphone

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：