Diversified service recommendation with high accuracy and efficiency

Wang, Lina; Zhang, Xuyun; Wang, Ruili; Yan, Chao; Kou, Huaizhen; Qi, Lianyong

doi:10.1016/j.knosys.2020.106196

Cited by 71 publications

(44 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the follow-up work, the real-world experiments are designed and performed to further validate the feasibility and effectiveness of PSRASk+S approach. In addition, as the diversity is a significance criterion for evaluating the performance of various decision-making systems [34][35][36][37], we go on improving our work to provide diverse and high-quality recommendation results [38][39][40][41] when government officials search for public sports resource allocation strategies.…”

Section: Discussionmentioning

confidence: 99%

Fuzzy Keywords-Driven Public Sports Resource Allocation Strategies Retrieval With Privacy-Preservation

Sang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Currently, the government proposes various public sports resource allocation strategies to promote the construction of public sports in the local. Thus, searching for the document database becomes an economic and efficient way for government officials to understand the contents of various public sports resource allocation strategies. As the government officials lack background knowledge of public sports resource allocation, the government officials are hard to retrieve appropriate documents. What's more, the document database is generally unwilling to share all text document information with the government official as some documents contain sensitive data information. Considering the above drawbacks, we put forward a fuzzy keywords-driven public sports resource allocation strategies retrieval approach based on the Simhash (named PSRASk+S) in the paper. The retrieval approach can accurately recommend appropriate documents to the government officials, by using the text description mining of documents and the fuzzy keywords search technology. Furthermore, the retrieval process is not revealing the sensitive data information of the irrelevant public sports resource allocation strategy document to the government officials, so the retrieval process can achieve local information protection mechanism. Finally, a case study explains the feasibility and effectiveness of our retrieval approach step by step.

show abstract

Section: Discussionmentioning

confidence: 99%

Fuzzy Keywords-Driven Public Sports Resource Allocation Strategies Retrieval With Privacy-Preservation

Sang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the current state-of-the-art, deep neural network compression can be conducted in two approaches: i) compressing the trained models by optimizing the network parameters and ii) designing and training small network models directly [29].…”

Section: Related Workmentioning

confidence: 99%

Lightweight image classifier using dilated and depthwise separable convolutions

Sun

Zhang

2020

J Cloud Comp

View full text Add to dashboard Cite

The image classification based on cloud computing suffers from difficult deployment as the network depth and data volume increase. Due to the depth of the model and the convolution process of each layer will produce a great amount of calculation, the GPU and storage performance of the device are extremely demanding, and the GPU and storage devices equipped on the embedded and mobile terminals cannot support large models. So it is necessary to compress the model so that the model can be deployed on these devices. Meanwhile, traditional compression based methods often miss many global features during the compression process, resulting in low classification accuracy. To solve the problem, this paper proposes a lightweight neural network model based on dilated convolution and depthwise separable convolution with twenty-nine layers for image classification. The proposed model employs the dilated convolution to expand the receptive field during the convolution process while maintaining the number of convolution parameters, which can extract more high-level global semantic features to improve the classification accuracy. Also, the depthwise separable convolution is applied to reduce the network parameters and computational complexity in convolution operations, which reduces the size of the network. The proposed model introduces three hyperparameters: width multiplier, image resolution, and dilated rate, to compress the network on the premise of ensuring accuracy. The experimental results show that compared with GoogleNet, the network proposed in this paper improves the classification accuracy by nearly 1%, and the number of parameters is reduced by 3.7 million.

show abstract

“…Privacy is a serious issue in edge computing as users data is collected, processed, transmitted, and shared over edge nodes, so it is becoming a necessity to secure user privacy before these data are integrated together [3]. The explosive growth and variety of information available on edge nodes frequently overwhelm users, recommender systems are a promising way for users to quickly find the valuable information that they are interested in from massive data [4,5,6]. In addition to these challenges, edge computing introduces a scale of cyber security challenges regular data center operators may not be used to dealing with.…”

Section: Introductionmentioning

confidence: 99%

A Novel Two-phase Cycle Algorithm for Effective Cyber Intrusion Detection in Edge Computing

Gong

Liu

Yin

2020

Preprint

View full text Add to dashboard Cite

Edge computing extends traditional cloud services to the edge of the network, closer to users, and is suitable for network services with low latency requirements. With the rise of edge computing, its security issues have also received more and more attention. In this paper, a novel two-phase cycle algorithm is proposed for effective cyber intrusion detection in edge computing based on multi-objective genetic algorithm (MOGA) and modified back propagation neural network (MBPNN), namely TPC-MOGA-MBPNN. In the first phase, the MOGA is employed to build multi-objective optimization model that tries to find Pareto optimal parameter set for MBPNN. The Pareto optimal parameter set is applied for simultaneous minimization of average false positive rate (Avg FPR), mean squared error (MSE), and negative average true positive rate (Avg TPR) in the dataset. In the second phase some MBPNNs are created based on the parameter set obtained by MOGA and are trained to search for more optimal parameter set locally. The parameter set obtained in the second phase is used as the input of the first phase, and the training process is repeated until the termination criteria are reached. Benchmark dataset namely KDD cup 1999 is used to demonstrate and validate the performance of the proposed approach for intrusion detection. The proposed approach can discover a pool of MBPNN based solutions. Combining these MBPNN can significantly improve prediction performance, and a GA is used to find the optimal MBPNN combination. The result shows that the proposed approach could reach an accuracy of 98.81% and a detection rate of 98.23%, which outperform most systems of previous works found in the literature. In addition, the proposed approach is a generalized classification approach that is applicable to the problem of any field having multiple conflicting objectives.

show abstract

Diversified service recommendation with high accuracy and efficiency

Cited by 71 publications

References 27 publications

Fuzzy Keywords-Driven Public Sports Resource Allocation Strategies Retrieval With Privacy-Preservation

Fuzzy Keywords-Driven Public Sports Resource Allocation Strategies Retrieval With Privacy-Preservation

Lightweight image classifier using dilated and depthwise separable convolutions

A Novel Two-phase Cycle Algorithm for Effective Cyber Intrusion Detection in Edge Computing

Contact Info

Product

Resources

About