Information fusion for edge intelligence: A survey

Zhang, Yin; Jiang, Chi; Yue, Binglei; Guizani, Mohsen

doi:10.1016/j.inffus.2021.11.018

Cited by 57 publications

(17 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evolving from Multi-source Information Fusion, Intelligence Fusion employs multi-tiered processing, filtering, and correlation techniques across a range of information types to achieve high-fidelity state and identity estimations, as well as battlefield situation and threat evaluations (Zhang et al, 2022). These information sources include but are not confined to sensors, databases, knowledge repositories, and an array of human-centric data like statistics, textual content, imagery, audio, and video.…”

Section: Information Fusion and Intelligence Fusionmentioning

confidence: 99%

A paradigm shift in crisis management: The nexus of AGI‐driven intelligence fusion networks and blockchain trustworthiness

Yue,

Shyu

2024

Contingencies & Crisis Mgmt

View full text Add to dashboard Cite

In an era characterized by vast data streams and complex socioeconomic dynamics, the fusion and precise analysis of multi‐sourced intelligence has emerged as a pivotal challenge. To address this, the study constructs a sophisticated intelligence fusion network (IFN) architecture leveraging the potential of Artificial General Intelligence (AGI) and the security tenets of blockchain technology. Drawing from diverse fields including informatics, computer science, data analytics, and network security, the research adopts an integrative methodology comprising both a comprehensive literature review and systems analysis. Key findings highlight the prowess of AGI‐driven IFNs in enhancing governmental early warning systems for crisis management. These networks underscore a paradigm shift from reactive postevent measures to proactive pre‐event forecasting, thus bolstering the efficacy of governmental responses. Moreover, the decentralized nature of blockchain technology ensures data integrity, fostering trust in interdepartmental data sharing—an essential for efficient crisis management in hierarchical administrative structures. This study accentuates the need for redefining crisis management strategies, emphasizing data‐driven decision‐making and seamless intelligence sharing to ensure optimal outcomes.

show abstract

Section: Information Fusion and Intelligence Fusionmentioning

confidence: 99%

A paradigm shift in crisis management: The nexus of AGI‐driven intelligence fusion networks and blockchain trustworthiness

Yue,

Shyu

2024

Contingencies & Crisis Mgmt

View full text Add to dashboard Cite

show abstract

“…For information coverage grey numbers, data fusion is generally divided into three levels: estimation theory, uncertainty reasoning method, and the theory of intelligent computing and pattern recognition (Zhang et al, 2022c), of which uncertain reasoning methods are mainly used to solve uncertain problems of multisource heterogeneous data (Rao et al, 2022). Uncertain reasoning methods include the subjective Bayesian method (Goldstein, 2006), the DS evidence reasoning method (Dai et al, 1999), the DSm-T method (Zhao et al, 2022), and the cloud model (Li et al, 2009).…”

Section: Literature Reviewmentioning

confidence: 99%

Dynamic Multi-Attribute Evaluation of Digital Economy Development in China: A Perspective From Interaction Effect

Xiao,

Gao,

Chen

et al. 2023

Technological and Economic Development of Economy

View full text Add to dashboard Cite

This study aims to reflect the grey information coverage and complex interactions effect in digital economy development. Therefore, a multi-attribute decision making method based on the grey interaction relational degree of the normal cloud matrix (GIRD-NCM) model is proposed. First, the original information coverage grey numbers are transformed into normal cloud matrixes, and then a novel Minkowski distance between normal clouds is proposed by using different information principles. Second, the GIRD-NCM model is established according to the Choquet fuzzy integral and grey relational degree. Finally, the dynamic comprehensive evaluation of digital economy development in China from 2013 to 2020 is conducted. The implementation, availability, and feasibility of the GIRD-NCM model are verified by comparative analysis with three existing evaluation models. The empirical findings reveal a stable growth trend in China’s digital economy, with an annual growth rate of 7.87%, however, there are notable regional development disparities. The change in interaction degree has no effect on the rankings of provinces that are in the lead or have a moderately high level of digital economy development, but has a positive and negative impact on the rankings of these provinces with high and low levels of digital economy development, respectively.

show abstract

“…Federated Learning (FL [8,12]) is a promising distributed machine learning approach that enables mobile local clients to build a powerful global model by collaborating with a global server. The mobile devices share a local model developed from the sensitive data accessible to those devices without sharing the sensitive data with other parties.…”

Section: Federated Learningmentioning

confidence: 99%

“…2. Drebin:This dataset contains features from 15036 app samples where 9476 are benign and 5560 are android malwares from Drebin project [12]. It also contains 215 features.…”

Section: Dataset Descriptionmentioning

confidence: 99%

A Dynamic Weighted Federated Learning for Android Malware Classification

Chaudhuri¹,

NANDI²,

Pradhan³

2023

Preprint

View full text Add to dashboard Cite

<p>Android malware attacks are increasing daily at a tremendous volume, making Android users more vulnerable to cyber-attacks. Researchers have developed many machine learning (ML)/ deep learning (DL) techniques to detect and mitigate android malware attacks. However, due to technological advancement, there is a rise in android mobile devices. Furthermore, the devices are geographically dispersed, resulting in distributed data. In such scenario, traditional ML/DL techniques are infeasible since all of these approaches require the data to be kept in a central system; this may provide a problem for user privacy because of the massive proliferation of Android mobile devices; putting the data in a central system creates an overhead. Also, the traditional ML/DL-based android malware classification techniques are not scalable. Researchers have proposed federated learning (FL) based android malware classification system to solve the privacy preservation and scalability with high classification performance. In traditional FL, Federated Averaging (FedAvg) is utilized to construct the global model at each round by merging all of the local models obtained from all of the customers that participated in the FL. However, the conventional FedAvg has a disadvantage: if one poor-performing local model is included in global model development for each round, it may result in an under-performing global model. Because FedAvg favors all local models equally when averaging. To address this issue, our main objective in this work is to design a dynamic weighted federated averaging (DW-FedAvg) strategy in which the weights for each local model are automatically updated based on their performance at the client. The DW-FedAvg is evaluated using four popular benchmark datasets, Melgenome, Drebin, Kronodroid and Tuandromd used in android malware classification research. The results show that our proposed approach is scalable, privacy preserved, and capable of outperforming the traditional FedAvg for android malware classification in terms of accuracy, F1 score, AUC score and FPR score.</p>

show abstract

Information fusion for edge intelligence: A survey

Cited by 57 publications

References 84 publications

A paradigm shift in crisis management: The nexus of AGI‐driven intelligence fusion networks and blockchain trustworthiness

A paradigm shift in crisis management: The nexus of AGI‐driven intelligence fusion networks and blockchain trustworthiness

Dynamic Multi-Attribute Evaluation of Digital Economy Development in China: A Perspective From Interaction Effect

A Dynamic Weighted Federated Learning for Android Malware Classification

Contact Info

Product

Resources

About