Multimodal and ontology-based fusion approaches of audio and visual processing for violence detection in movies

In this paper we present our research results towards the detection of violent scenes in movies, employing advanced fusion methodologies, based on learning, knowledge representation and reasoning. Towards this goal, a multi-step approach is followed: initially, automated audio and visual analysis is performed to extract audio and visual cues. Then, two different fusion approaches are deployed: (i) a multimodal one that provides binary decisions on the existence of violence or not, employing machine learning techniques, (ii) an ontological and reasoning one, that combines the audio-visual cues with violence and multimedia ontologies. The latter reasons out not only the existence of violence or not in a video scene, but also the type of violence (fight, screams, gunshots). Both approaches are experimentally tested, validated and compared for the binary decision problem of violence detection. Finally, results for the violence type identification are presented for the ontological fusion approach. For evaluation purposes, a large dataset of real movie data has been populated.     

Degradation of the insecticide azinphos methyl in orange and peach juices during storage at different temperatures

The degradation of azinphos methyl in orange and peach juice was studied. The insecticide was aseptically added to packed orange and peach juices and stored at 40, 20 and 0°C. Samples were removed at regular intervals and were analysed for residues of azinphos methyl. Residues were determined with a simple gas-chromatographic method using a 30m glass capillary column and an NP detector. The recoveries of azinphos methyl were 87-110% for orange juice and 92-108% for peach juice, and the limit of determination was 0.004mg/kg for both juices. From the experimental data, rate constants, half-lives, and times needed to reach legal limits for the decomposition of azinphos methyl in orange and peach juices were evaluated. Half-lives for orange and peach juices were 6.5 and 7.8 days at 40°C, 86.6, and 92.4 days at 20°C, and 407.7 and 495.1 days at 0°C, respectively.     

Heraclitus: A Framework for Semantic Web Adaptation

The World Wide Web's constant growth and transformation offers great opportunities - and poses many challenges for exploitation. The semantic Web has emerged as a possible answer to these challenges by offering an approach in organizing and sharing the Web, but it doesn't explicitly consider user needs and requirements. Heraclitus is a framework for semantic Web adaptation in which user needs and requirements are the driving force, using text and Web usage mining to support Web site ontology and topology evolution. The result is improved user interaction with the semantic Web     

Analytical modelling of plastic behaviour of uniformly FRP confined concrete members

A method is presented for the assessment and calibration of the elastoplastic behaviour of FRP confined concrete. The method is based on the evaluation of permanent deformations from observed experimental deformations and theoretical elastic response of confined concrete. The inelastic response of concrete and the parameters of its mathematical modelling are investigated. Closed form expressions are produced to relate the model parameters to the mechanical properties of the material. A strain-hardening Drucker–Prager model is developed which simulates both the hardening and softening material response with reasonable agreement to the experimental observations. The predictive ability of the model is verified through comparisons to numerous published experimental data and analytical models.     

Dependent mixtures of Dirichlet processes

An approach to modeling dependent nonparametric random density functions is presented. This is based on the well known mixture of Dirichlet process model. The idea is to use a technique for constructing dependent random variables, first used for dependent gamma random variables. While the methodology works for an arbitrary number of dependent random densities, with each pair having their own dependent structure, the mathematics and estimation algorithm is focused on two dependent random density functions. Simulations and a real data example are presented.     

The MoveOn database: motorcycle environment speech and noise database for command and control applications

The MoveOn speech and noise database was purposely designed and implemented in support of research on spoken dialogue interaction in a motorcycle environment. The distinctiveness of the MoveOn database results from the requirements of the application domain—an information support and operational command and control system for the two-wheel police force—and also from the specifics of the adverse open-air acoustic environment. In this article, we first outline the target application, motivating the database design and purpose, and then report on the implementation details. The main challenges related to the choice of equipment, the organization of recording sessions, and some difficulties that were experienced during this effort, are discussed. We offer a detailed account of the database statistics, the suggested data splits in subsets, and discuss results from automatic speech recognition experiments which illustrate the degree of complexity of the operational environment.     

框架结构弹塑性分析的一种有效数值方法

框架结构的不完全弹塑性分析是一个非线性过程,按照假定的加载模式,利用荷载因子进行逐步加载。基于力学和数值方法,研究框架结构的极限承载力和变形能力。假定材料为理想弹塑性,并利用零长度塑性铰模拟塑性行为。该方法基于增量方程,类似于求解两个连续塑性铰之间的凸二次参数规划问题。利用虚荷载因子将凸二次参数规划转化为凸二次规划,并使用标准算法求解凸二次规划问题,可满足出现塑性铰的要求并自动判别塑性。该方法起初仅适用于纯弯作用,后延伸至弯矩-轴力共同作用。分别分析单调、变化、循环加载作用下的算例。整个过程稳定、可靠、高效,并比基于直接刚度法的交替位移方法更省时。