嵌入式数字视频监控系统的数据存储策略

在基于vxWorks的嵌入式数字视频监控系统中实现了先进的存储策略,克服了dosFs文件系统自身的缺陷与不足,满足了实际应用的要求。

A Fast and Memory-Efficient Approach to NDN Name Lookup

For name-based routing/switching in NDN, the key challenges are to manage large-scale forwarding Tables, to lookup long names of variable lengths, and to deal with frequent updates. Hashing associated with proper length-detecting is a straightforward yet efficient solution. Binary search strategy can reduce the number of required hash detecting in the worst case. However, to assure the searching path correct in such a schema, either backtrack searching or redundantly storing some prefixes is required, leading to performance or memory issues as a result. In this paper, we make a deep study on the binary search, and propose a novel mechanism to ensure correct searching path without neither additional backtrack costs nor redundant memory consumptions. Along any binary search path, a bloom filter is employed at each branching point to verify whether a said prefix is present, instead of storing that prefix here. By this means, we can gain significantly optimization on memory efficiency, at the cost of bloom checking before each detecting. Our evaluation experiments on both real-world and randomly synthesized data sets demonstrate our superiorities clearly

Single-particle 3D reconstruction on specialized stream architecture and comparison with GPGPUs

The wide acceptance and data deluge in medical imaging processing require faster and more efficient systems to be built.Due to the advances in heterogeneous architectures recently,there has been a resurgence in the first research aimed at FPGA-based as well as GPGPU-based accelerator design.This paper quantitatively analyzes the workload,computational intensity and memory performance of a single-particle 3D reconstruction application,called EMAN,and parallelizes it on CUDA GPGPU architectures and decouples the memory operations from the computing flow and orchestrates the thread-data mapping to reduce the overhead of off-chip memory operations.Then it exploits the trend towards FPGA-based accelerator design,which is achieved by offloading computingintensive kernels to dedicated hardware modules.Furthermore,a customized memory subsystem is also designed to facilitate the decoupling and optimization of computing dominated data access patterns.This paper evaluates the proposed accelerator design strategies by comparing it with a parallelized program on a 4-cores CPU.The CUDA version on a GTX480 shows a speedup of about 6 times.The performance of the stream architecture implemented on a Xilinx Virtex LX330 FPGA is justified by the reported speedup of 2.54 times.Meanwhile,measured in terms of power efficiency,the FPGA-based accelerator outperforms a 4-cores CPU and a GTX480 by 7.3 times and 3.4 times,respectively.

PROXY-BASED PATCHING STREAM TRANSMISSION STRATEGY IN MOBILE STREAMING MEDIA SYSTEM

A mobile transmission strategy, PMPatching (Proxy-based Mobile Patching) transmission strat-egy is proposed, it applies to the proxy-based mobile streaming media system in Wideband Code Division Multiple Access (WCDMA) network. Performance of the whole system can be improved by using patching stream to transmit anterior part of the suffix that had been played back, and by batching all the demands for the suffix arrived in prefix period and patching stream transmission threshold period. Experimental results show that this strategy can efficiently reduce average network transmission cost and number of channels consumed in central streaming media server.

Negotiation Strategies of Myanmar Migrant Workers in the Sidhiphatra Cold Storage Factory, Songkhla Province

This paper studies the Myanmar migrant workers in Sidhiphatra Cold Storage Factory, Songkhla Province. This factory employs just over 2,000 Myanmar migrant workers. The authors study their ＂everyday life practices＂ as expressed in relationships among various groups, such as relationships between the Myanmar migrant workers and the factory, and the relationships between the Myanmar migrant workers and the Thai people of the surrounding communities. In analyzing these relationships and negotiations, the authors borrow the concept of ＂tactics of everyday life＂ from Michel de Certeau as a framework for analysis. The authors＇ analyses are based on in-depth interviews, non-participant observations, and focus-group discussions that collectively explored the tactics, in de Certeau＇s sense, that the Myanmar migrant workers used in negotiating their relationships with the factory and with the various communities in the area. The results indicate that Myanmar migrant workers negotiate their relationship with the factory by expressing themselves as selected workers, good workers, and being obedient to the factory＇s rules. The conflicts caused by Myanmar and Cambodian migrant workers are negotiated. Besides, Myanmar migrant workers also negotiate their relationship with the Thai people living in the surrounding communities. Their approach is showing that they are part of the communities by participating in the activities with the aim to gain acceptance of the Thai people in the surrounding communities.

A Practical Group Key Management Algorithm for Cloud Data Sharing with Dynamic Group

Cloud data sharing service, which allows a group of people to work together to access and modify the shared data, is one of the most popular and efficient working styles in the enterprises. However, the cloud server is not completely trusted, and its security could be compromised by monetary reasons or caused by hacking and hardware errors. Therefore, despite of having advantages of scalability and flexibility, cloud storage service comes with privacy and the security concerns. A straightforward method to protect the user's privacy is to encrypt the data stored at the cloud. To enable the authenticated users to access the encrypted cloud data, a practical group key management algorithm for the cloud data sharing application is highly desired. The existing group key management mechanisms presume that the server is trusted. But, the cloud data service mode does not always meet this condition. How to manage the group keys to support the scenario of the cloud storage with a semi-trusted cloud server is still a challenging task. Moreover, the cloud storage system is a large-scale and open application, in which the user group is dynamic. To address this problem, we propose a practical group key management algorithm based on a proxy re-encryption mechanism in this paper. We use the cloud server to act as a proxy tore-encrypt the group key to allow authorized users to decrypt and get the group key by their private key. To achieve the hierarchical access control policy, our scheme enables the cloud server to convert the encrypted group key of the lower group to the upper group. The numerical analysis and experimental results further validate the high efficiency and security of the proposed scheme.

Cation-mixing stabilized layered oxide cathodes for sodium-ion batteries

Sodium-ion batteries are promising for large-scale energy storage due to sodium's low cost and infinite abundance. The most popular cathodes for sodium-ion batteries, i.e., the layered sodium-containing oxides, usually exhibit reversible host rearrangement between P-type and O-type stacking upon charge/discharge. Herein we demonstrate that such host rearrangement is unfavorable and can be suppressed by introducing transition-metal ions into sodium layers. The electrode with stabilized P3-type stacking delivers superior rate capability, high energy efficiency, and excellent cycling performance. Owing to the cation-mixing nature, it performs the lowest lattice strain among all reported cathodes for sodium-ion batteries. Our findings highlight the significance of a stable host for sodium-ion storage and moreover underline the fundamental distinction in material design strategy between lithium-and sodium-ion batteries.

Pegasus：a distributed and load-balancing fingerprint identification system

Fingerprint has been widely used in a variety of biometric identification systems in the past several years due to its uniqueness and immutability. With the rapid development of fingerprint identification techniques, many fingerprint identification systems are in urgent need to deal with large-scale fingerprint storage and high concurrent recognition queries, which bring huge challenges to the system. In this circumstance, we design and implement a distributed and load-balancing fingerprint identification system named Pegasus, which includes a distributed feature extraction subsystem and a distributed feature storage subsystem. The feature extraction procedure combines the Hadoop Image Processing Interface（HIPI） library to enhance its overall processing speed; the feature storage subsystem optimizes MongoD B＇s default load balance strategy to improve the efficiency and robustness of Pegasus.Experiments and simulations are carried out, and results show that Pegasus can reduce the time cost by 70% during the feature extraction procedure. Pegasus also balances the difference of access load among front-end mongos nodes to less than 5%. Additionally, Pegasus reduces over 40% of data migration among back-end data shards to obtain a more reasonable data distribution based on the operation load（insertion, deletion, update, and query） of each shard.