检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Yadav, Vanshika Hajarnis, Pratham Minu, R.I. Srm Institute of Science and Technology Computing Technologies Chennai India

ISBN: (纸本)9798331509828

In this ever-evolving field of studies, clinical trials demand efficiency and data security. The project will investigate the integration of blockchain, in combination with quantum technology in solving challenges faced by current clinical trials. This would help in streamlining trial management to guarantee that data is transparent, traceable, and tamper-proof. Data tampering, delays in recruitment, and inefficient data systems contribute to slow trials. Most traditional systems lack transparency;hence, data verification can be exhausting, as well as compliance with regulations. The processes involved in patient consent and data sharing are too long. To this end, blockchain provides an immutable ledger relevant for transactions of data with the goal of making the data record transparent and traceable. On the other hand, smart contracts will automate the process of patient consent and the mode of data sharing to minimize the administrative burden to build trust, while quantum technology - or for precision QKD - is to improve the security features of block-chain to face future quantum computer attacks, compromising traditional encryption. Testing and simulation results showed that blockchain integrated with quantum technology will increase information security, reduce costs, accelerate patient recruitment, and speed up data management. Blockchain enables tamper-proof, verifiable entries, while QKD provides strong protection against future cyber threats. This dual-technology approach is, therefore, the solution to the inefficiencies and security vulnerabilities of clinical trials. The project allows further innovations in the pipeline, which quickens the delivery of new treatments to patients with security and efficiency in mind. © 2025 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Privacy and Security Concerns in Edge-Cloud Systems: An In-Depth Analysis 3

Privacy and Security Concerns in Edge-Cloud Systems: An In-D...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kaki, Samuel Suhas Kantareddygari, Jagadeswara Reddy Aishwarya, R. School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798331527549

Edge-Cloud systems provide efficient computation and storage close to data sources, with lower latency, scalability, and application performance for various applications, such as IoT, autonomous vehicles, and real-time analytics. These systems are highly vulnerable to significant security and privacy challenges, which include the following: data confidentiality and integrity in the process of transmission, secure protection of sensitive data stored on the edge against physical and remote attacks, and maintaining availability under dynamic network conditions. More challenges related to ensuring users' private nature through anonymizing data, obtaining consent for all processes involved, and compliance with specific regulations like GDPR and CCPA. This work incorporates more enhanced cryptographic methods in the transfer of data between heterogeneous systems and environment-based anomaly detection, advanced privacy-preserving analytics to avoid extraction of private data, adaptive control mechanisms in place for Edge-Cloud for minimizing vulnerability with enhanced trust along with the maintenance of data integrity. The key benefits would be robust mitigation of threats, better interoperability between edge and cloud platforms, and alignment with evolving security standards, which promotes wider adoption across various sectors. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Scalability and Reliability of Port Simulation Workflow on Slurm 15th

Scalability and Reliability of Port Simulation Workflow on...

引用

15th International Conference on Parallel Processing and Applied Mathematics, PPAM 2024

作者： Drozdowski, Maciej Wawrzyniak, Jakub Marszalkowski, Jakub Institute of Computing Science Poznań University of Technology Poznań Poland

ISBN: (纸本)9783031856990

Parallelizing of container terminal seaside layout optimizer using a Slurm cluster is considered in this paper. Maritime container terminals have quays divided into discrete berth segments. The number of berths and their lengths have to be adjusted to the arriving vessel traffic for high quality of service. A particular partition of the terminal quay into berths is called terminal layout. The vessel traffic is represented by the stochastic ship traffic model (STM). An instantiation of the STM is a specific ship arrival scenario. Evaluation of a quay layout on an arrival scenario requires scheduling vessels on the berths, which is a classic Berth Allocation Problem (BAP) of maritime logistics. The problem of partitioning terminal quay into berths, subject to vessel traffic, for high quality of service will be called a Stochastic Quay Partitioning Problem (SQPP). In this paper, we present a hill-climber metaheuristic for SQPP. The process of the partition evaluation is conducted on a Slurm cluster by a simple workflow. We report on the scalability and reliability of this workflow. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

SecuDroid : Android Malware Detection using ML classifier on Static Features 2

SecuDroid : Android Malware Detection using ML classifier on...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Vanusha, D. Singh, Shashank Jha, Abhijeet Kumar Delsi Robinsha, S. School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798350365269

The Android operating system's widespread use has unfortunately made it a target for malware attacks, underlining the necessity for robust detection strategies. Existing literature has explored the potential of machine learning in combating Android malware, often employing a mix of static and dynamic analyses. However, a major portion of these malwares are zero-day vulnerabilities. In this context, our study makes a significant contribution by focusing on using static features extracted from Android application package (APK) files to differentiate between benign and malicious applications. Specifically, all training and testing in this study were performed on the Drebin-215 dataset, a comprehensive collection known for its relevance in Android security research. Improving malware detection using static features allows for detection of malwares before they are run on devices. We analyzed five ML classification algorithms, beginning with a Decision Tree, followed by SVM (Support Vector Machine) with an RBF kernel, then moving to Logistic Regression and K-Nearest Neighbor, and finally, we introduced our proposed model, the SecuDroid Neural Network - employing a methodology that employs precise hyper-parameter tuning, and evaluation through stratified 4-fold cross-validation. The evaluation on an unseen test dataset, based on accuracy, F1-score, and AUC metrics, revealed the SecuDroid Neural Network surpassed its counterparts by reaching an accuracy of 0.993, an F1-score of 0.991, and an AUC of 0.999. Our findings not only offer a comparative analysis of different machine learning models for malware detection but also introduce an efficient approach, thereby enriching the arsenal against Android malware threats, with all empirical validations grounded in the Drebin-215 dataset. © 2024 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

An effective object detection and tracking using automated image annotation with inception based faster R-CNN model

引用

International Journal of Cognitive computing in Engineering 2024年第1期5卷 343-356页

作者： Vijiyakumar, K. Govindasamy, V. Akila, V. Department of Computing Technologies School of computing SRM institute of Science and Technology Kattankulathur campus Tamilnadu Chengalpattu district India Department of Information Technology Pondicherry Engineering College Pondicherry India Department of Computer Science and Engineering Pondicherry Engineering College Pondicherry India

The present study advances object detection and tracking techniques by proposing a novel model combining Automated Image Annotation with Inception v2-based Faster RCNN (AIA-IFRCNN). The research methodology utilizes the DCF-CSRT model for image annotation, Faster RCNN for object detection, and the inception v2 model for feature extraction, followed by a softmax layer for image classification. The proposed AIA-IFRCNN model is evaluated on three benchmark datasets: Bird (Dataset 1), UCSDped2 (Dataset 2), and Under Water (Dataset 3), to determine prediction accuracy, annotation time, Center Location Error (CLE), and Overlap Rate (OR). The experimental results indicate that the AIA-IFRCNN model outperformed existing models regarding detection accuracy and tracking performance. Notably, it achieved a maximum detection accuracy of 95.62 % on Dataset 1, outperforming other models. Additionally, it achieved minimum average CLE values of 4.16, 5.78, and 3.54, and higher overlap rates of 0.92, 0.90, and 0.94 on the respective datasets (1, 2 and 3). Hence, this research work on object detection and tracking using the AIA-IFRCNN model is essential for improving system efficiency and fostering innovation in the field of computer vision and object tracking. © 2024

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition for Phrase Interpretation: A Deep Learning Approach

Gesture Recognition for Phrase Interpretation: A Deep Learni...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Puyam, Kelvin Singh, Nishant Aruna, M. SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350375237

Gesture recognition holds paramount significance in facilitating communication for individuals utilizing sign language to convey phrases and expressions. We present an innovative approach to gesture recognition in this article tailored for interpreting hand signs to derive meaningful phrases, such as 'I love you,' 'please,' 'sorry,' and 'goodbye.' Our proposed methodology integrates a multi-box detector (SSD) with dynamic hand gesture analysis to achieve real-time and accurate recognition of hand signs across various languages and cultural contexts. By harnessing the power of deep learning SSD for object detection, our system ensures swift responses while maintaining precision. Additionally, the incorporation of dynamic hand gesture analysis techniques enhances the system's adaptability to diverse sign styles and linguistic nuances, thus fostering better communication access. By means of meticulous experimentation, we establish the effectiveness of our methodology in precisely identifying and deciphering real-time sign language gestures, attaining noteworthy results in terms of both speed and accuracy. This study enhances assistive technology for hard-of-hearing and deaf communities, thereby promoting accessibility and inclusiveness in communication environments that are accommodated to the linguistic requirements of a variety of individuals. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Model-Heterogeneous Federated Graph Learning With Prototype Propagation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 676-689页

作者： Liu, Zhi Zhou, Hanlin He, Xiaohua Yuan, Haopeng Du, Jiaxin Wang, Mengmeng Shen, Guojiang Kong, Xiangjie Xia, Feng Zhejiang University of Technology College of Computer Science & Technology Hangzhou310023 China RMIT University School of Computing Technologies MelbourneVIC3000 Australia

Federated graph learning (FGL) enables clients to collaboratively train a robust graph neural network (GNN) while ensuring their private graph data never leaves the local. However, existing FGL frameworks require all clients to train the identical GNN model, which limits their real-world applicability. Although many model-heterogenous frameworks have been proposed for traditional nongraph federated learning settings, directly transferring them to the FGL setting typically results in suboptimal performance. To fill the gap, this article presents federated prototype propagation network (FedPPN), a lightweight FGL framework that supports clients to train fully customized models. FedPPN only transmits prototypes between clients and the server for knowledge sharing. The core idea is propagating global prototypes on each client's local graph, generating prototype-based node representations and predictions. The prototype-based prediction can then be ensembled with the prediction of local GNN, allowing clients to achieve accurate prediction. We evaluate our FedPPN on six benchmark datasets with different heterogeneous model setups. Experimental results show that our FedPPN outperforms advanced baselines in model accuracy without adding any trainable parameters on clients or the server. Besides, FedPPN's communication cost is significantly lower than methods that rely on model parameter exchange. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Facial Action Unit Recognition Enhanced by Text Descriptions of FACS

引用

IEEE Transactions on Affective computing 2025年第2期16卷 814-826页

作者： Chang, Yanan Zhang, Caichao Wu, Yi Wang, Shangfei University of Science and Technology of China Key Lab of Computing and Communication Software of Anhui Province Anhui Hefei230027 China

Although the descriptions of facial action units (AUs) provide crucial semantic knowledge for representation learning from facial images, they have not been fully explored for facial action unit recognition. In this paper, we propose a method that effectively explores the knowledge existing in AU descriptions to enhance AU recognition. Specifically, the proposed method consists of three components, i.e., AU recognition network, global representation alignment, and AU representation alignment. The AU recognition network extracts global features and AU-specific features for AU prediction from images. To leverage AU textual descriptions fully, we design two-level representation alignment for AU recognition. The global representation alignment component closes the distance between the global facial features and its corresponding positive global embedding extracted from textual descriptions. Then, the AU-specific features are aligned with the positive AU textual embedding by the AU representation alignment component. Negative textual embedding generation strategies are also designed to further boost the two-level representation alignment. Through the two-level alignment, AU textual descriptions guide image representation learning of the AU recognition network. Experiments on two benchmark datasets and one in-the-wild dataset demonstrate the efficacy of the description-enhanced AU recognition method, compared with the state-of-the-art works. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TM2SP: A Transformer-based Multi-Level Spatiotemporal Feature Pyramid Network for Video Saliency Prediction

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5236-5250页

作者： Li, Chenming Liu, Shiguang Tianjin University School of Computer Science and Technology College of Intelligence and Computing Tianjin300350 China Tianjin University Tianjin Key Laboratory of Cognitive Computing and Application Tianjin300350 China

This paper proposes an end-to-end video saliency prediction network model, termed TM2SP-Net (Transformer-based Multi-level Spatiotemporal Feature Pyramid Network). Leveraging the strong encoding learning capability of Video Swin Transformer for video data, we design a Multi-level Spatiotemporal Feature Pyramid Network (MLSTFPN) that effectively detects and enriches salient regions and spatial details across different scales. In particular, a pre-trained image saliency detection encoder is employed to extract salient features from each frame, serving as prior knowledge to guide the multi-scale spatiotemporal feature fusion and decoding processes. Additionally, we introduce an Inception Gate-Controlled Fusion (IGCF) and Layered Self-Attention Aggregation Fusion (LSAF) mechanisms to efficiently merge spatiotemporal features across various stages. Finally, extensive experiments conducted on the DHF1K, Hollywood-2, UCF-Sports, and six audio-visual saliency datasets demonstrate the superiority of our method over existing state-of-the-art approaches. © 1991-2012 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Manifold Dual Contouring Algorithms Based on k-d tree and Octree Data Structures

引用

Informatica (Slovenia) 2024年第3期48卷 399-418页

作者： Ramaijane, Thabang Hlomani, Hlomani Zlotnikova, Irina Maupong, Thabiso Department of Computing and Informatics School of Pure and Applied Sciences Botswana International University of Science and Technology Botswana Botswana

This study evaluated the performance and efficiency of manifold dual contouring algorithms using k-d trees and octrees, therefore, addressing a critical gap in comparative analysis of these data structures. Despite the popularity of k-d trees and octrees in isosurface extraction, their performance has not been empirically compared. This research specifically focuses on visualization quality, performance metrics, and efficiency across various simplification error thresholds. A comprehensive comparative analysis was conducted to identify the conditions under which each data structure is most suitable. Both algorithms employed the manifold vertex clustering scheme for dual contouring of isosurfaces. The methodology involved evaluating visual output, build time, extraction time, and efficiency based on triangle counts during the simplification process. Computational experiments demonstrated that the octree-based algorithm is superior for rendering large models, producing an average of 20% more visual detail due to a higher triangle count. In contrast, the k-d tree-based algorithm showed a 40% reduction in build time and a 35% reduction in extraction time, making it more efficient for processing large implicit models by reducing geometric complexity. These findings provide metrics to assist researchers and practitioners in selecting the most suitable adaptive data structure for achieving optimal simplification results in manifold dual contouring algorithm implementations. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Trees (mathematics)

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：