Improving Speech Recognition Accuracy for Small Vocabulary Applications in Adverse Environments

The problem of improving the accuracy of small vocabulary isolated word speaker dependent speech recognition under adverse conditions such as factory environments is considered. A new approach to solving this problem, by using Output Probability Distributions (OPDs), is presented. OPDs improve the system performance by modelling inter-word relationships, something that a standard maximum likelihood (ML) technique fails to do. The system was tested using the TI46 database, corrupted with the NOISEX-92 database, as well as in a real-world factory environment, and achieved good results.     

场地受限条件下大跨度门式 启闭机安装实例

通过对特定的门式启闭机安装场地条件进行实地考查,列出了场地条件对其安装作业存在的不利因素。在分析研究了由于场地存在的不利因素对门式启闭机安装造成的难题后,有针对性地制定了安装技术措施,从而保证了安装作业过程安全、实施顺利。本文可供类似场地条件的门式启闭机安装施工作业参考。     

浙东地区水资源配置工程管理对策研究

浙东引水工程是一项优化浙东地区水资源配置格局、解决浙东地区水资源短缺矛盾的系统工程。工程建成后,如何进行科学调度和有效运行管理,以获得最大综合效益,是摆在水利部门面前的重要课题。通过对浙东引水工程的特点和面临的问题进行全面剖析,研究提出建立管理体系、制定统一调度方案、建立水量水质监测系统等对策建议,为浙东引水工程建成后的运行调度管理提供决策参考。     

强震区砂砾石筑坝技术进展

现代工程技术的长足发展,让我国西部强震区建设高混凝土面板和沥青心墙砂砾石坝成为可能。在分析国内外砂砾石坝的基础上,对砂砾石筑坝的工程特性、填筑标准与材料分区进行了研究,提出了解决其抗震稳定性的措施,包括合理的坝体材料分区设计、加强坝体抗震措施和施工技术进步等。     

太湖流域水灾害应急对策研究

太湖流域是我国经济社会高度发达的地区之一,发生水灾害时往往会造成重大经济损失。对发生各类水灾害时的应急对策展开研究总结,以减轻水灾害,避免人员伤亡,保障经济社会可持续健康稳定发展,并通过分析典型案例的实际应对过程,为今后开展类似工作提供参考。     

Feature selection for classification of oscillating time series

We propose a forward sequential feature selection scheme based on k‐means clustering algorithm to derive the feature subset that classifies best the time series data base, according to the criterion of the corrected Rand index. Moreover, we investigate the effect of the standardization scheme on the feature selection and propose a standardization given by the transform to standard Gaussian distribution. Our interest in this work is in classification of oscillating dynamical systems on the basis of measures computed on time series from these systems. The features to be selected are measures of linear and non‐linear analysis of time series, such as auto‐correlation and Lyapunov exponents, as well as oscillation characteristics, such as the mean magnitude of peaks. Simulations on known oscillating deterministic and stochastic systems showed that, for repeated realizations of the same classification task, the proposed feature selection scheme selected very often the same best feature subset, giving high classification accuracy for any standardization. We found that, regardless of the standardization, the highest classification accuracy could be obtained with a small feature subset, containing most frequently an oscillating‐related feature. The same setting was applied to records of epileptic electroencephalogram signals, giving varying results and dependent on the standardization.     

Robust quantification of the exposure to operational risk: Bringing economic sense to economic capital

Operational risk is commonly analyzed in terms of the distribution of aggregate yearly losses. Risk measures can then be computed as statistics of this distribution that focus on the region of extreme losses. Assuming independence among the operational risk events and between the likelihood that they occur and their magnitude, separate models are made for the frequency and for the severity of the losses. These are then combined to estimate the distribution of aggregate losses. While the detailed form of the frequency distribution does not significantly affect the risk analysis, the choice of model for the severity often has a significant impact on operational risk measures. For heavy-tailed distributions these measures are dominated by extreme losses, whose probability cannot be reliably extrapolated from the available data. With limited empirical evidence, it is difficult to distinguish among alternative models that produce very different values of the risk measures. Furthermore, the estimates obtained can be unstable and overly sensitive to the presence or absence of single extreme events. Setting a bound on the maximum amount that can be lost in a single event reduces the dependence on the distributional assumptions and improves the robustness and stability of the risk measures, while preserving their sensitivity to changes in the risk profile. This bound should be determined by expert assessment on the basis of economic arguments and validated by the regulator, so that it can be used as a control parameter in the risk analysis.     

Emerging university student experiences of learning technologies across the Asia Pacific

Three hundred students across eight countries and eleven higher education institutions in the Asia Pacific Region participated in two courses on climate change and disaster management that were supported by learning technologies: a satellite-enabled video-conferencing system and a learning management system. Evaluation of the student experience across the region proved a significant challenge, particularly the way the students conceived of the links between the technologies and their studies, and the way they approached the use of the technologies in connected and sometimes disconnected ways. This study examines the results of a quantitative investigation into the student experience and identifies key aspects of the structure of the variables used to evaluate the experience as well as identifying groups of students in the sample population who reported qualitatively different experiences. Significant outcomes reveal that cohesive conceptions of the learning technologies tend to be related to more effective ways of using both the video-conferencing and learning management systems, and that both at the level of variables, and at the level of groups of students, these experiences tend to be related to relatively higher outcomes. The results have important implications for both the design and teaching of technology-mediated courses and offer ideas for courses that combine systems such as learning management and video-conferencing.     

The effects of organizational learning environment factors on e-learning acceptance

Workplace learning is an important means of employees’ continuous learning and professional development. E-learning is being recognized as an important supportive practice for learning at work. Current research on the success factors of e-learning in the workplace has emphasized on employees’ characteristics, technological attributes, and training design elements, with little attention to workplace contextual effects. The study aims to investigate the impacts of organizational learning environment factors, including managerial support, job support, and organizational support, on employees’ motivation to use a workplace e-learning system. A model was proposed based on the expectancy theory of training motivation and the social influences and facilitating conditions in technology acceptance models. The model was tested on sample data collected from mainland China using Structural Equation Modeling and Moderated Structural Equation Modeling. The results suggested that employees’ perceived managerial support and job support had a significant impact on their perceived usefulness of the e-learning system for individual learning, and that perceived organizational support had a significant influence on the perceived usefulness of the e-learning system for social learning. Perceived usefulness for individual learning was found to completely mediate the environmental influences on individuals’ motivation to use the system, while perceived usefulness for social learning made partial mediation in the effects of the environmental factors on intention to use. In addition, perceived job support was found to have moderating effects on the relationship between employees’ perceived usefulness of the e-learning system and their intention to use the system. Consistent with previous findings, employees’ perceptions about the usefulness of the e-learning system have significant effects on their intention to use the system in the work setting.     

TROPHI: development of a tool to measure complex,multi-factorial patient handling interventions

Patient handling interventions are complex and multi-factorial. It has been difficult to make comparisons across different strategies due to the lack of a comprehensive outcome measurement method. The Tool for Risk Outstanding in Patient Handling Interventions (TROPHI) was developed to address this gap by measuring outcomes and comparing performance across interventions. Focus groups were held with expert patient handling practitioners (n = 36) in four European countries (Finland, Italy, Portugal and the UK) to identify preferred outcomes to be measured for interventions. A systematic literature review identified 598 outcome measures; these were critically appraised and the most appropriate measurement tool was selected for each outcome. TROPHI was evaluated in the four EU countries (eight sites) and by an expert panel (n = 16) from the European Panel of Patient Handling Ergonomics for usability and practical application. This final stage added external validity to the research by exploring transferability potential and presenting the data and analysis to allow respondent (participant) validation.

Practitioner Summary: Patient handling interventions are complex and multi-factorial and it has been difficult to make comparisons due to the lack of a comprehensive outcome measurement method. The Tool for Risk Outstanding in Patient Handling Interventions (TROPHI) was developed to address this gap by measuring outcomes to compare performance across interventions.