Level of interest sensing in spoken dialog using decision-level fusion of acoustic and lexical evidence

Automatic detection of a user's interest in spoken dialog plays an important role in many applications, such as tutoring systems and customer service systems. In this study, we propose a decision-level fusion approach using acoustic and lexical information to accurately sense a user's interest at the utterance level. Our system consists of three parts: acoustic/prosodic model, lexical model, and a model that combines their decisions for the final output. We use two different regression algorithms to complement each other for the acoustic model. For lexical information, in addition to the bag-of-words model, we propose new features including a level-of-interest value for each word, length information using the number of words, estimated speaking rate, silence in the utterance, and similarity with other utterances. We also investigate the effectiveness of using more automatic speech recognition (ASR) hypotheses (n-best lists) to extract lexical features. The outputs from the acoustic and lexical models are combined at the decision level. Our experiments show that combining acoustic evidence with lexical information improves level-of-interest detection performance, even when lexical features are extracted from ASR output with high word error rate.     

乡镇矿山科学管理出效益的体会

柳树沟磷矿开工时技术力量十分薄弱，以自己培养为主．广泛争取设计院等单位支持．基建工程严格按设计施工，并且建立健全各项规章制度，实行科学管理，安全生产文明生产，扩大生产规模，已由年产９万ｔ扩大到２０万ｔ，企业经济效益、社会效益十分显著，成为乡镇矿山典范，磷矿企业的标兵．     

Jet bundle formulation of infinite-dimensional port-Hamiltonian systems using differential operators

We consider infinite-dimensional port-Hamiltonian systems described on jet bundles. Based on a power balance relation we introduce the port-Hamiltonian system representation using differential operators regarding the structural mapping, the dissipation mapping and the input mapping. In contrast to the well-known representation on the basis of the underlying Stokes–Dirac structure our approach is not necessarily based on using energy-variables which leads to a different port-Hamiltonian representation of the analyzed partial differential equations. The presented constructions will be specialized to mechanical systems to which class also the presented examples belong.     

Manipulability of leader–follower networks with the rigid-link approximation

This paper introduces the notion of manipulability to mobile, multi-agent networks as a tool to analyze the instantaneous effectiveness of injecting control inputs at certain, so-called leader nodes in the network. Effectiveness is interpreted to characterize how the movements of the leader nodes translate into responses among the remaining follower nodes. This notion of effectiveness is a function of the interaction topologies, the agent configurations, and the particular choice of inputs used to influence the network. In fact, classic manipulability is an index used in robotics to analyze the singularity and efficiency of configurations of robot-arm manipulators. To define similar notions for leader–follower networks, we use a rigid-link approximation of the follower dynamics and, under this assumption, we prove that the instantaneous follower velocities can be uniquely determined from that of the leaders’, which allows us to define a meaningful and computable manipulability index for the leader–follower networks. This paper examines the property of the proposed index in simulation and with real mobile robots, and demonstrates how the index can be used to find effective interaction topologies.     

Security concepts for the dynamics of autonomous vehicle networks

The secure operation of autonomous vehicle networks in the presence of adversarial observation is examined, in the context of a canonical double-integrator-network (DIN) model. Specifically, we study the ability of a sentient adversary to estimate the full network’s state, from noisy local measurements of vehicle motions. Algebraic, spectral, and graphical characterizations are provided, which indicate the critical role of the inter-vehicle communication topology and control scheme in achieving security.     

Saturation-based switching anti-windup design for linear systems with nested input saturation

This paper proposes a saturation-based switching anti-windup design for the enlargement of the domain of attraction of a linear system subject to nested saturation. A nestedly saturated linear feedback is expressed as a linear combination of a set of auxiliary linear feedbacks, which form a convex hull where the nestedly saturated linear feedback resides. This set of auxiliary linear feedbacks is then partitioned into several subsets. The auxiliary linear feedbacks in each of these subsets form a convex sub-hull of the original convex hull. When the value of the nestedly saturated linear feedback falls into a convex sub-hull, it can be expressed as a linear combination of the subset of all the auxiliary feedbacks that form the convex sub-hull. A separate anti-windup gain is designed for each convex sub-hull by using a common quadratic Lyapunov function and is implemented when the value of the nestedly saturated linear feedback falls into this convex sub-hull. Simulation results indicate that such a saturation-based switching anti-windup design has the ability to significantly enlarge the domain of attraction of the closed-loop system.     

枯草杆菌碱性磷酸酶制备的最佳工艺条件及酶促反应动力学性质的研究

以枯草杆菌为菌种液体培养制备碱性磷酸酶，研究确定了培养的最佳工艺条件，并对碱性磷酸酶的酶促反应动力学性质进行了初步探讨。结果表明，枯草杆菌制备碱性磷酸酶的最佳工艺条件为：40℃，pH值7．4振荡培养10h，酶活最高。对碱性磷酸酶的动力学性质研究表明，该酶催化底物磷酸苯二钠水解反应的最适pH值8．8，最适温度52℃，米氏常数Km值为2．94mmol／L。     

高效液相色谱法测定卷柏中的穗花杉双黄酮

用反相高效液相色谱法测定卷柏提取物中的穗花杉双黄酮。结果表明：穗花杉双黄酮在质量浓度为41.2mg／L～206mg／L时，峰面积Y与其质量浓度X的线性关系良好，回归方程为Y=547．028X 15．4895(r=0.9999)，最低检测限为2．0μg/L；穗花杉双黄酮的平均回收率为99．42％(n=3)，相对标准偏差RSD为0．79％；连续进样、日内进样和日间进样所得检测结果的RSD分别为0．12％、0．11％和0．11％。     

Cloud based intelligent system for delivering health care as a service

The promising potential of cloud computing and its convergence with technologies such as mobile computing, wireless networks, sensor technologies allows for creation and delivery of newer type of cloud services. In this paper, we advocate the use of cloud computing for the creation and management of cloud based health care services. As a representative case study, we design a Cloud Based Intelligent Health Care Service (CBIHCS) that performs real time monitoring of user health data for diagnosis of chronic illness such as diabetes. Advance body sensor components are utilized to gather user specific health data and store in cloud based storage repositories for subsequent analysis and classification. In addition, infrastructure level mechanisms are proposed to provide dynamic resource elasticity for CBIHCS. Experimental results demonstrate that classification accuracy of 92.59% is achieved with our prototype system and the predicted patterns of CPU usage offer better opportunities for adaptive resource elasticity.     

Computer aided detection system for micro calcifications in digital mammograms

Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. Mammogram breast X-ray is considered the most reliable method in early detection of breast cancer. However, it is difficult for radiologists to provide both accurate and uniform evaluation for the enormous mammograms generated in widespread screening. Micro calcification clusters (MCCs) and masses are the two most important signs for the breast cancer, and their automated detection is very valuable for early breast cancer diagnosis. The main objective is to discuss the computer-aided detection system that has been proposed to assist the radiologists in detecting the specific abnormalities and improving the diagnostic accuracy in making the diagnostic decisions by applying techniques splits into three-steps procedure beginning with enhancement by using Histogram equalization (HE) and Morphological Enhancement, followed by segmentation based on Otsu's threshold the region of interest for the identification of micro calcifications and mass lesions, and at last classification stage, which classify between normal and micro calcifications ‘patterns and then classify between benign and malignant micro calcifications. In classification stage; three methods were used, the voting K-Nearest Neighbor classifier (K-NN) with prediction accuracy of 73%, Support Vector Machine classifier (SVM) with prediction accuracy of 83%, and Artificial Neural Network classifier (ANN) with prediction accuracy of 77%.