With the privacy issues drawing more and more concerns,privacy protection techniques based on Computational Private Information Retrieval (CPIR) allow a user to retrieve data from a service provider without revealing the users query information.For large-scale applications,there exists a gap between privacy protection techniques and its feasibility.For the problem that the CPIR algorithm needs long computing time so as not to be suitable for large-scale data privacy protection,this paper proposes a CPIR nearest neighbor privacy protection algorithm (H-PCPIR-V) based on Spark and Huffman code.The H-PCPIR-V algorithm partitions the spatial data into Voronoi diagrams according to the points of interest in the data preprocessing stage,and then utilizes the Huffman code to compress the candidate data in order to reduce bit computation operation.Spark parallel framework is used for query grid parallel computing in the server side.The experimental results show that the computational cost of HPCPIR-V algorithm is about 30 ％ lower than that of PCPIR-V algorithm on the server side,the computational cost of client is about 10％ lower,and the communication cost is about 40％ lower.

The massive online open course ( MOOC) is mainly dependent on video,the lecturer can not directly access to the student′s state of listening. However in the face-to-face course,the lecturer can timely access to the feedback,and improve the teaching process through the student′s facial expression. In order to solve this problem,the student′sfacial expression identification was introducedinto MOOC,7 kinds of expressions are defined,and a dynamic expression recognition algorithm is explored. Firstly,the face images are ex-tracted from the video captured by camera at 5 frames intervals, and then its are processed by FACE + + to select facial feature points. Secondly,the selected several feature modes of the important parts of face studied by the SVM are convert to the nodes of the classification tree. Finally,the facial expressions are recognized by the combination of feature modes of the important face parts. Exper-iment shows that the algorithm does not be limited to recognize the 6 kinds of traditional facial expression recognition,it has better effect on the MOOC.

In this era of big data, more and more models need to be trained to mine useful knowledge from large scale data. It has become a challenging problem to train multiple models accurately and efficiently so as to make full use of limited computing resources. As one of ELM variants, online sequential extreme learning machine (OS-ELM) provides a method to learn from incremental data. MapReduce, which provides a simple, scalable and fault-tolerant framework, can be utilized for large scale learning. In this paper, we propose an efficient parallel method for batched online sequential extreme learning machine (BPOS-ELM) training using MapReduce. Map execution time is estimated with historical statistics, where regression method and inverse distance weighted interpolation method are used. Reduce execution time is estimated based on complexity analysis and regression method. Based on the estimations, BPOS-ELM generates a Map execution plan and a Reduce execution plan. Finally, BPOS-ELM launches one MapReduce job to train multiple OS-ELM models according to the generated execution plan, and collects execution information to further improve estimation accuracy. Our proposal is evaluated with real and synthetic data. The experimental results show that the accuracy of BPOS-ELM is at the same level as those of OS-ELM and parallel OS-ELM (POS-ELM) with higher training efficiencies.

To address the low-efficiency problem for query privacy protection on big data, parallel CPIR-V (PCPIR-V), which had a high level of privacy protection for nearest neighbor query, was presented and implemented based on spark. Two parallel strategies for PCPIR-V, Row strategy and Bit strategy, were proposed. To avoid redun-dant multiplications, the repeated products were cached based on a clustering technique while computing CPIR on Spark. According to the evaluation results of PCPIR-V on three datasets, the scalablity of PCPIR-V is good until the number of core is larger than 40. The cost of PCPIR-V with the method of caching partial multiplication results is reduced by 20% averagely.