Assessing the representativeness of a smartphone-based household travel survey in Dar es Salaam,Tanzania

The household travel survey (HTS) finds itself in the midst of rapid technological change. Traditional methods are increasingly being sidelined by digital devices and computational power—for tracking movements, automatically detecting modes and activities, facilitating data collection, etc.. Smartphones have recently emerged as the latest technological enhancement. FMS is a smartphone-based prompted-recall HTS platform, consisting of an app for sensor data collection, a backend for data processing and inference, and a user interface for verification of inferences (e.g., modes, activities, times, etc.). FMS, has been deployed in several cities of the global north, including Singapore. This paper assesses the first use of FMS in a city of the global south, Dar es Salaam. FMS in Dar was implemented over a 1-month period, among 581 adults chosen from 300 randomly selected households. Individuals were provided phones with data plans and the FMS app preloaded. Verification of the collected data occurred every 3 days, via a phone interview. The experiment reveals various social and technical challenges. Models of individual likelihood to participate suggest little bias. Several socioeconomic and demographic characteristics apparently do influence, however, the number of days fully verified per individual. Similar apparent biases emerge when predicting the likelihood of a given day being verified. Some risk of non-random, non-response is, thus, evident.     

Optimal Threshold Policies for Robust Data Center Control

With the simultaneous rise of energy costs and demand for cloud computing, efficient control of data centers becomes crucial. In the data center control problem, one needs to plan at every time step how many servers to switch on or off in order to meet stochastic job arrivals while trying to minimize electricity consumption. This problem becomes particularly challenging when servers can be of various types and jobs from different classes can only be served by certain types of server, as it is often the case in real data centers. We model this problem as a robust Markov decision process (i.e., the transition function is not assumed to be known precisely). We give sufficient conditions (which seem to be reasonable and satisfied in practice) guaranteeing that an optimal threshold policy exists. This property can then be exploited in the design of an efficient solving method, which we provide. Finally, we present some experimental results demonstrating the practicability of our approach and compare with a previous related approach based on model predictive control.     

Research on Web Page Classification Method Based on Query Log

Web page classification is an important application in many fields of Internet information retrieval, such as providing directory classification and vertical search. Methods based on query log which is a light weight version of Web page classification can avoid Web content crawling, making it relatively high in efficiency, but the sparsity of user click data makes it difficult to be used directly for constructing a classifier. To solve this problem, we explore the semantic relations among different queries through word embedding, and propose three improved graph structure classification algorithms. To reflect the semantic relevance between queries, we map the user query into the low-dimensional space according to its query vector in the first step. Then, we calculate the uniform resource locator (URL) vector according to the relationship between the query and URL. Finally, we use the improved label propagation algorithm (LPA) and the bipartite graph expansion algorithm to classify the unlabeled Web pages. Experiments show that our methods make about 20% more increase in F1-value than other Web page classification methods based on query log.     

Modeling and simulation of a counter-rotating turbine system for underwater vehicles

The structure of a counter-rotating turbine of an underwater vehicle is designed by adding the counter-rotating second-stage turbine disk after the conventional single-stage turbine. The available kinetic energy and the absorption power of the auxiliary system are calculated at different working conditions, and the results show that the power of the main engine and auxiliary system at the counter-rotating turbine system matches well with each other. The experimental simulation of the lubricating oil loop, fuel loop, and seawater loop are completed right before the technology scheme of the counter-rotating turbine system is proposed. The simulation results indicate that the hydraulic transmission system can satisfy the requirements for an underwater vehicle running at a steady sailing or variable working conditions.     

Real-Time Fault Diagnosis for Gas Turbine Blade Based on Output-Hidden Feedback Elman Neural Network

In order to remotely monitor and maintain large-scale complex equipment in real time, China Telecom plans to create a total solution that integrates remote data collection, transmission, storage, analysis and prediction. This solution can provide manufacturers with proactive, systematic, integrated operation and maintenance service, and the data analysis and health forecasting are the most important part. This paper conducts health management for the turbine blades. Elman neural network, and improved Elman neural network, i.e., outputhidden feedback (OHF) Elman neural network are studied as the main research methods. The results verify the applicability of OHF Elman neural network.     

基于深度强化学习的智能船舶航迹跟踪控制

[目的]智能船舶的航迹跟踪控制问题往往面临着控制环境复杂、控制器稳定性不高以及大量的算法计算等问题。为实现对航迹跟踪的精准控制,提出一种引入深度强化学习技术的航向控制器。[方法]首先,结合视线(LOS)算法制导,以船舶的操纵特性和控制要求为基础,将航迹跟踪问题建模成马尔可夫决策过程,设计其状态空间、动作空间、奖励函数;然后,使用深度确定性策略梯度(DDPG)算法作为控制器的实现,采用离线学习方法对控制器进行训练;最后,将训练完成的控制器与BP-PID控制器进行对比研究,分析控制效果。[结果]仿真结果表明,设计的深度强化学习控制器可以从训练学习过程中快速收敛达到控制要求,训练后的网络与BP-PID控制器相比跟踪迅速,具有偏航误差小、舵角变化频率小等优点。[结论]研究成果可为智能船舶航迹跟踪控制提供参考。