新闻视频中基于“场景词汇”的故事单元相似度分析

新闻视频中故事单元的相似度计算对于视频浏览、检索和跟踪故事单元等应用具有特别重要的意义.研究提出了一种利用"场景词汇"计算故事单元相似度的方法,将单独的关键帧作为一个完整"词汇",将每个故事单元看作是一系列"场景词汇"描述的"文档".在此基础上研究了"场景词汇"的特殊性,并设计了有效的"场景词汇"权重计算方法和故事单元相似度计算方法.实验显示,基于"场景词汇"的故事单元相似度计算方法能够比较好地贴近用户感官和实际应用需求.     

Optimal production ramp-up in the smartphone manufacturing industry

Motivated by challenges in the smartphone manufacturing industry, we develop a dynamic production ramp-up model that can be applied to economically satisfy nonstationary demand for short-life-cycle products by high-tech companies. Due to shorter life cycles and more rapid evolution of smartphones, production ramp-up has been increasingly critical to the success of a new smartphone. In the production ramp-up, the key challenge is to match the increasing capacity to nonstationary demand. The high-tech smartphone manufacturers are urged to jointly consider the effect of increasing capacity and decreasing demand. We study the production planning problem using a high-dimensional Markov decision process (MDP) model to characterize the production ramp-up. To address the curse of dimensionality, we refine Monte Carlo tree search (MCTS) algorithm and theoretically analyze its convergence and computational complexity. In a real case study, we find that the MDP model achieves revenue improvement by stopping producing the existing product earlier than the benchmark policy. In synthetic instances, we validate that the proposed MCTS algorithm saves computation time without loss of solution quality compared with traditional value iteration algorithm. As part of the Lenovo production solution, our MDP model enables high-tech smartphone manufacturers to better plan the production ramp-up.     

Solving partially observable agent‐intruder games with an application to border security problems

In this paper, we introduce partially observable agent‐intruder games (POAIGs). These games model dynamic search games on graphs between security forces (an agent) and an intruder given possible (border) entry points and high value assets that require protection. The agent faces situations with dynamically changing, partially observable information about the state of the intruder and vice versa. The agent may place sensors at selected locations, while the intruder may recruit partners to observe the agent's movement. We formulate the problem as a two‐person zero‐sum game, and develop efficient algorithms to compute each player's optimal strategy. The solution to the game will help the agent choose sensor locations and design patrol routes that can handle imperfect information. First, we prove the existence of ?‐optimal strategies for POAIGs with an infinite time horizon. Second, we introduce a Bayesian approximation algorithm to identify these ?‐optimal strategies using belief functions that incorporate the imperfect information that becomes available during the game. For the solutions of large POAIGs with a finite time horizon, we use a solution method common to extensive form games, namely, the sequence form representation. To illustrate the POAIGs, we present several examples and numerical results.     

Maintaining systems with heterogeneous spare parts

We consider the problem of optimally maintaining a stochastically degrading, single‐unit system using heterogeneous spares of varying quality. The system's failures are unannounced; therefore, it is inspected periodically to determine its status (functioning or failed). The system continues in operation until it is either preventively or correctively maintained. The available maintenance options include perfect repair, which restores the system to an as‐good‐as‐new condition, and replacement with a randomly selected unit from the supply of heterogeneous spares. The objective is to minimize the total expected discounted maintenance costs over an infinite time horizon. We formulate the problem using a mixed observability Markov decision process (MOMDP) model in which the system's age is observable but its quality must be inferred. We show, under suitable conditions, the monotonicity of the optimal value function in the belief about the system quality and establish conditions under which finite preventive maintenance thresholds exist. A detailed computational study reveals that the optimal policy encourages exploration when the system's quality is uncertain; the policy is more exploitive when the quality is highly certain. The study also demonstrates that substantial cost savings are achieved by utilizing our MOMDP‐based method as compared to more naïve methods of accounting for heterogeneous spares.     

Competitive location and capacity decisions for firms serving time‐sensitive customers

In this article we explore how two competing firms locate and set capacities to serve time‐sensitive customers. Because customers are time‐sensitive, they may decline to place an order from either competitor if their expected waiting time is large. We develop a two‐stage game where firms set capacities and then locations, and show that three types of subgame perfect equilibria are possible: local monopoly (in which each customer is served by a single firm, but some customers may be left unserved), constrained local monopoly (in which firms serve the entire interval of customers but do not compete with each other), and constrained competition (in which firms also serve the entire interval of customers, but now compete for some customers). We perform a comparative statics analysis to illustrate differences in the equilibrium behavior of a duopolist and a coordinated monopolist. © 2008 Wiley Periodicals, Inc. Naval Research Logistics, 2008     

Continuous sampling plans for markov-dependent production processes

This article discusses the behavior of three continuous sampling plans: continuous sampling plan 1 (CSP 1) and continuous sampling plan 2 (CSP 2) developed by Dodge [5] and Dodge and Torrey [7], and multilevel continuous sampling plan 2 (MLP 2) developed by Lieberman and Solomon [11], when the quality of successive units in a continuous production process follows a two-state time-homogeneous Markov chain. We first derive the average outgoing quality (AOQ) expressions of these plans. Exact procedures for determining the average outgoing quality limit (AOQL) can be obtained only for CSP 1. For CSP 2 and MLP 2 plans, iterative procedures have been used to obtain the AOQL contours. For these plans, it is assumed that the serial correlation coefficient between the two consecutive random variables of the Markov chain is known. In addition, estimation procedures for the coefficient are given. We show that if the serial correlation coefficient of the Markov chain is positive (negative), the AOQL is increased (decreased) as compared to the case when the successive units in the production process follows a Bernoulli pattern. Let r denote the number of production units examined in succession which are found to be of good quality and k denote the inverse of the sampling fraction employed when quality is good. Then if r and k are sufficiently small, it is observed from the graph that, for small departures of the serial correlation coefficient from zero, the AOQL values do not differ significantly for each of the three plans; whereas for sufficiently large values of r and k, the AOQL values differ significantly. Various aspects of these plans, such as their operating characteristics 2 (OC 2) and the serial correlation coefficient, are discussed.     

A decomposition procedure for convex quadratic programs

This article deals with the solution of convex quadratic programs by iteratively solving a master problem and a subproblem as proposed previously by Sacher. The approach has the advantage that the subproblems are linear programs so that advantage can be taken of existing schemes for solving large linear problems. At each step in solving the master problem, a closed-form solution can be specified so that the procedure is well suited for solving large quadratic programs and can take advantage of the constraint structure.     

Multiple criteria decision making in the USSR: A survey

A brief historical overview of the development of multiple criteria decision making (MCDM) in the USSR during the last fifteen years is presented. Soviet MCDM research is reviewed. Several applications of MCDM methodology in the USSR are described. Long-term trends in the research and application of MCDM in the Soviet Union are discussed.     

Modeling the performance of a scanning radio communications sensor

A model which allows the prediction of long-term average report rates against an array of radio emitters by a scanning sensor is presented. The model is based on Markov renewal theory.     

Bounds and properties of the expected value of sample information for a project-selection problem

In this article we extend the work of Mehrez and Stulman [5] on the expected value of perfect information (EVPI) to the expected value of sample information (EVSI) for a class of economic problems dealing with the decision to reject or accept an investment project. It is shown that shifting the mean of the underlying a priori distribution of X, the project's monetary value from zero in either direction will decrease the associated EVSI of Y, the random sampled information. A theorem is then presented which gives an upper bound on the EVSI over all distributions of Y, as well as the structure of the posterior mean E[X|Y] for which this upper bound is achieved. Finally, the case where E[X|Y] is linear in Y is discussed and its performance compared with that of the optimal case.