Use Learnable Knowledge Graph in Dialogue System for Visually Impaired Macro Navigation

Dialogue in natural language is the most important communication method for the visually impaired. Therefore, the dialogue system is the main subsystem in the visually impaired navigation system. The purpose of the dialogue system is to understand the user’s intention, gradually establish context through multiple conversations, and finally provide an accurate destination for the navigation system. We use the knowledge graph as the basis of reasoning in the dialogue system, and then update the knowledge graph so that the system gradually conforms to the user’s background. Based on the experience of using the knowledge graph in the navigation system of the visually impaired, we expect that the same framework can be applied to more fields in order to improve the practicality of natural language dialogue in human–computer interaction.

Redundancy Allocation Optimization for Multistate Systems With Failure Interactions Using Semi-Markov Process

Failure interactions and multiple states are two common phenomena in engineering systems. However, most of the redundancy allocation problems assume binary states and ignore failure interactions, which will cause inaccurate and misleading results. Although some research work focuses on the multistate systems, failure interactions have been ignored. This paper, for the first time, solves the redundancy allocation problems considering the systems having both multiple states and failure interactions. The system studied in this paper is a kind of multistate system containing a main subsystem and an auxiliary subsystem with the failure interaction existing from the auxiliary subsystem to the main subsystem. Semi-Markov process is proposed as the model for the system analysis, and a reliability measure, availability, is obtained based on the proposed semi-Markov process models. The system availability is used as the constraint in the redundancy allocation problem. A case study from a navy application is presented to demonstrate the applicability of the proposed method.

RELIABILITY AND SENSITIVITY ANALYSIS OF AN OPERATING SYSTEM WITH INSPECTION IN DIFFERENT WEATHER CONDITIONS

This paper deals with the reliability analysis of a system which consists of two subsystems namely main and standby with two weather conditions — normal and abnormal (turbulent). The subsystems are nonidentical and each has two modes — normal and total failure. The main subsystem is k-to-l-out-of-n and standby subsystem is k-out-of-n configurations. Single repairman is available for repair who plays the dual role of inspection and repair. Repairman inspects main subsystem and both the subsystems at its failure to see the feasibility of repair. If repair of the (sub) system is not feasible, it is replaced by new one. Inspection activities are stopped in abnormal weather conditions but system remains operative. Failure rates of both subsystems and the rate of change of weather conditions are constant, whereas the repair rates are general. With the help of Supplementary variable technique, Laplace transformations and copula methodology the transition state probabilities, asymptotic behavior and some characteristics such as reliability, availability, M.T.T.F., cost effectiveness and sensitivity of the system have been evaluated. At last some particular cases and numerical examples have been taken to describe the model.