In this paper, we point out that SSDs may give a new opportunity in performance enhancement of virtualization environment. By the analysis of virtio, a de-facto standard framework for virtual I/O devices and the evaluation experiments of original version of virtio, we show that in order to get better scalability for SSDs, virtio needs to be redesign on the new assumption that requests of different types from different VMs are quite independent. Under such an assumption, a new framework is designed based on virtio, which is sirtio, as we put scalability the first place. According to our evaluation, sirtio can improve the scalability of SSDs in virtualization environment.
An algorithm to reconstruct images with Least Squares Support Vector Machines (LS-SVM) and Simulated Annealing Particle Swarm Optimization (APSO) is provided, which is named as SAP. In order to overcome the soft field characteristics of ECT sensitivity field, we exercised some image samples of typical flow pattern with LS-SVM so as to predict the capacitance error caused by the soft field characteristics and then construct the fitness function of the particle swarm optimization on basis of the capacitance error. This algorithm introduces simulated annealing ideas into PSO, adopts cooling process functions to replace the inertia weight function and construct the time variant inertia weight function featured in annealing mechanism, takes use of the APSO algorithm to search for the optimized resolution of Electrical Capacitance Tomography (ECT) reconstruction image. The simulation results show that SAP algorithm is featured in quick convergence rate and higher imaging precision. Compared with Land Weber algorithm and Newton-Raphson algorithm, the quality of reconstruction image with SAP is significantly improved.
Data is the primary concern in data mining. Data Stream Mining is gaining a lot of practical significance with the huge online data generated from Sensors, Internet Relay Chats, Twitter, Facebook, Online Bank or ATM Transactions. The primary constraint in finding the frequent patterns in data streams is to perform only one time scan of the data with limited memory and requires less processing time. The concept of dynamically changing data is becoming a key challenge, what we call as data streams. In our present work, the algorithm is based on finding frequent patterns in the data streams using a tree based approach.
Computer network has realized its popularization after years of development. For its high office efficiency, computer network is widely used by enterprises and campus. However, factors such as the operating system, viruses and Trojan horses have brought serious concealed danger to network security in the process of practical application. Combined with the present situation of computer network security, the work studied the security protection design of the network. Besides, the work also analyzed the multi-port transmission technology briefly from transmission equipment and characteristics.
Sophisticated industrial worms, such as Stuxnet, Flame, Duqu, have brought much threat in industrial networks. Most existing detection methods use content pattern or aggressive activities as a clue to the existence of worms, which are ineffective against worms that don't have their pattern been known and don't behave aggressively. To detect such worms, we proposed Cloud-based Behavior Similarity Transmission Method (CBSTM). CBSTM is a cloud-based method that utilizes the fundamental feature that a worm propagates from host to host. It monitors behaviors on each host in industrial networks. When same behaviors propagate among hosts and meet given criteria, corresponding hosts are believed to be infected by worms. When the worm is detected, the found behavior sequence is used as this worm's signature to realize instant worm detection afterwards. Since CBSTM doesn't need specific characteristics of worms, it can be generally applied to detecting any worms in industrial networks. The evaluation with detecting Stuxnet confirms the effectiveness of CBSTM.
