The distributed user trace collection and storage system based on interface window tree model

Xia, Qing; Lv, Jianghua; Ma, Shilong

doi:10.1007/s12652-020-01897-0

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e blockchain significant advantages, such as distributed storage [17], time-series data and tamper-resistant unforgeable, decentralization, and smart contracts automatic execution, and relying on distributed consensus agreement [18], satisfy trading integrity verification and improve the traditional data storage mode's low electronic degree, easy data loss, easy tampering, and inefficient legal service process. Blockchain technology is commonly used in different storage scenarios, such as in the field of cryptocurrency [19], medical care [20], agricultural product traceability [21], digital copyright [22], and legal [23].…”

Section: Blockchain Technology Blockchainmentioning

confidence: 99%

CL-BC: A Secure Data Storage Model for Social Networks

Wang

Zhu

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

While bringing convenience to people, social networks cause various security problems, such as information leakage, which belongs to the security category of data storage. The related research focuses more on the confidentiality design and lacks the discussion of data integrity protection technology. Thus, the electronic data editability invites the risk of data tampering and destruction, making other operations meaningless once the data are inaccurate. A social network-oriented data security storage model, CL-BC, included conceptual design, preliminary framework design, and detailed flow design, to improve the security threats such as overauthorization and illegal execution in data storage. The blockchain technology is combined with the improved Clark–Wilson model to achieve data integrity access control protection through execution rules and authentication rules. The system uses the subalgorithm of DR-BFT for reference when deploying the algorithm program and adopts the intelligent contract to complete the design rules. The experimental analysis shows the CL-BC model adapts to the actual security environment, ensures the data storage integrity in the social network stored process, and has application value.

show abstract

Section: Blockchain Technology Blockchainmentioning

confidence: 99%

CL-BC: A Secure Data Storage Model for Social Networks

Wang

Zhu

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…This model supports the prediction with both high-order and low-order features. Low-level features use a multitasking linear model, which fits nonlinear data and supports artificial feature engineering to effectively identify users’ fake behavior sequences and improve the predictive ability of the model [ 18 , 19 , 20 ]. The high-order features partially solve the defects of the original RNN model, support the long-term memory of user behavior sequences, and predict users’ purchase intentions more accurately [ 21 , 22 ].…”

Section: Introductionmentioning

confidence: 99%

A New Information-Theoretic Method for Advertisement Conversion Rate Prediction for Large-Scale Sparse Data Based on Deep Learning

Xia

et al. 2020

Entropy

Self Cite

View full text Add to dashboard Cite

With the development of online advertising technology, the accurate targeted advertising based on user preferences is obviously more suitable both for the market and users. The amount of conversion can be properly increased by predicting the user’s purchasing intention based on the advertising Conversion Rate (CVR). According to the high-dimensional and sparse characteristics of the historical behavior sequences, this paper proposes a LSLM_LSTM model, which is for the advertising CVR prediction based on large-scale sparse data. This model aims at minimizing the loss, utilizing the Adaptive Moment Estimation (Adam) optimization algorithm to mine the nonlinear patterns hidden in the data automatically. Through the experimental comparison with a variety of typical CVR prediction models, it is found that the proposed LSLM_LSTM model can utilize the time series characteristics of user behavior sequences more effectively, as well as mine the potential relationship hidden in the features, which brings higher accuracy and trains faster compared to those with consideration of only low or high order features.

show abstract