Software & Systems

Articles of journal № 1 at 2017 year.

Order result by: Public date | Title | Authors |

21. Scene geometry for detector precision improvement [№1 за 2017 год]
Authors: E.V. Shalnov, Konushin A.S.
Visitors: 7947
Object detection algorithms are the key component of any intelligent video content analysis systems. High computation requirements and low precision of existing methods restrain widespread acceptance of intelligent video content analysis. The paper introduces a novel algorithm that accelerates existing sliding window object detectors and increases their precision. This approach is based on the geometric properties of an observed scene. If the camera position in the scene is known, we can determine feasible sizes of detected objects in each location of an input image. Windows of other sizes cannot correspond to objects in a scene and thus could be skipped. It significantly decreases computation time. The proposed algorithm estimates feasible sizes of object for each location of an input image. We apply Neural Network (NN) to solve this task. A NN takes camera calibration parameters and window parameters as the input and determines if this configuration feasible or not. We train the NN on the synthetic dataset. It allows us to take into account a huge range of camera calibration parameters. We apply the NN to construct a map of feasible object sizes for the input scene. Thus the detector processes the feasible subset of windows. The performed evaluation reveals that the proposed algorithm accelerates processing by 70 % and increases precision of a detector.

22. Modelling and simulation of Black Hole attack on wireless networks [№1 за 2017 год]
Authors: V.V. Shakhov, A.N. Yurgenson, O.D. Sokolova
Visitors: 8655
The technologies based on wireless sensor networks can be used in a wide range of vital applications. There are several implementations of the Internet of Things architecture based on wireless sensor networks. For example, the core objective in the projects of the 7th Framework Programme funded by the European Union was to provide the technical foundation for WSN technology in IoT products and services. As wireless sensor networks based applications are deployed, security becomes an essential requirement. In this paper the authors discuss the state-of-arts for security issues in WSN. It is impossible in all cases to provide absolute protection and eliminate the consequences of intrusion. However, the effective range of protection mechanisms will significantly reduce the damage. To achieve this it is necessary to develop and explore appropriate mathematical models. The paper focuses on the attack named Black Hole. This attack has one of the most dangerous destructive information impacts. As a result, more than 90 % of the information transmitted to the sink may be lost. The direct transmission of information between the nodes in WSN is possible if they are within each other's radio reachability. Therefore, the unit disk graphs (UDG-graphs) might be used as a wireless network model. Communication in these networks are described by UDG-models the most appropriate. To simulate data transmission by the routing algorithm in the graph, a spanning tree is constructed. The authors have obtained the formula for calculating analytical estimates for some cases of a spanning tree structure. To assess the vulnerability of this tree to attacks the authors used the value “normalized number of vertices with lost information”. It shows the average number of vertices which lose information, divided by the total number of nodes on the tree. The analytical results are consistent with simulation results. The paper offers a counteracting method against Black Hole and provides the corresponding performance analysis as well.

23. Automatic syntactic analysis of chinese sentences by a restricted dictionary [№1 за 2017 год]
Authors: Yu Chuqiao, Bessmertny I.A.
Visitors: 7410
The paper considers a problem of natural language processing of Chinese texts. One of the relevant tasks in this area is automatic fact acquisition by a query since existing automatic translators are useless for this task. The suggested approach includes a syntactic analysis of phrases and matching parts of speech founded with a formalized query. The purpose of the study is direct fact extracting from original texts without translation. For this purpose the paper suggests to use an approach based on syntactic analysis of sentences from a text with further comparison of the found parts of speech with a formalized subject–object–predicate query. A key feature of the proposed approach is a lack of a segmentation phase of a hieroglyph sequence in a sentence by words. The bottleneck at this task is a dictionary because interpretation of a sentence is impossible without even a single word in the dictionary. To eliminate this problem the authors propose to identify a sentence model by function words while restraint of the dictionary could be compensated by automatic building of a thesaurus using statistical processing of a document corpus. The suggested approach is tested on a small topic where it demonstrates its robustness. There is also an analysis of temporal properties of the developed algorithm. As the proposed algorithm uses a direct-search method, the parsing speed for real tasks could be unacceptably low and this is a subject for further research.

◄ ← Preview | 1 | 2 | 3