Nowadays gigantic crowd-sourced data from mobile devices have become widely available in social networks, enabling the possibility of many important mining applications to improve quality our daily lives. While providing tremendous benefits, release network public will pose considerable threats users' privacy. In this paper, we investigate problem real-time spatio-temporal publishing networks with privacy preservation. Specifically, consider continuous publication population statistics and...

In this article, de Carvalho, Lu, and Moulin consider five risk-based strategies: equally weighted, equal-risk budget, contribution, minimum variance, maximum diversification. All strategies can be well described by exposure to the market-cap index four simple factors: low beta, small cap, residual volatility, value. This finding, in their view, is a major contribution understanding of such provides framework compare them. except equal-weighted strategy are defensive have lower volatility...

Nowadays gigantic crowd-sourced data collected from mobile phone users have become widely available, which enables the possibility of many important mining applications to improve quality our daily lives. While providing tremendous benefits, release these public will pose a considerable threat users' privacy. To solve this problem, notion differential privacy has been proposed provide with theoretical guarantee, and recently it applied in streaming publishing. However, most existing...

This article presents the most compelling empirical evidence yet of a low-risk anomaly in fixed-income markets. The authors show that portfolios invested bonds with lowest risk would have delivered largest positive alpha and highest Sharpe ratios, riskier negative ratios. results proved extremely robust were confirmed for government bonds, quasi-government foreign securitized collateralized corporate investment-grade high-yield emerging market aggregates some these universes. They considered...

Internet of things is a new technology system that consists number information technologies, and it's an important part developing mordern sevice industry. The advent changing the previous tradition networks. Based on things, smartphone Android connected with service-oriented robots by wireless communication, where it programmed based TCP socket, thus, controlling service robot can be realized. controlled to sing, dance, so according command, characteristics are visual portable, motion...

Kalman filtering problem for singular systems is dealt with, where the measurements consist of instantaneous and delayed ones, plant includes multiplicative noise. By utilizing standard value decomposition, restricted equivalent system presented, filters are given by using well-known re-organization innovation analysis lemma. The optimal filter original based on above recursive Riccati equations, a numerical example presented to show validity efficiency proposed approach, comparison between...

We considered five risk-based strategies: equally-weighted, equal-risk budget, contribution, minimum variance and maximum diversification. All can be well described by exposure to the market-cap index four simple factors: low-beta, small-cap, low-residual volatility value. This is, in our view, a major contribution understanding of such strategies provides framework compare them. except equally-weighted are defensive with lower than index. Equally-weighted is exposed small-cap stocks....

Aiming at the control and optimization problem of blast furnace gas (BFG) systems in steel industry, a knowledge-based optimal algorithm combining fuzzy rules extraction with neural networks (NNs) ensemble-based prediction is proposed. On one hand, model designed to extract expert knowledge from historical data industrial process after community detection, then, great deal scheduling employed compose rule base, which can be used for inference scheme new input. other data-driven NNs ensemble...

Mobile Robot Indoor Positioning System has wide application in the industry and home automation field. Unfortunately, existing mobile robot indoor positioning methods often suffer from poor accuracy, system instability, need for extra installation efforts. In this paper, we propose a novel which applies centralized method into robot, real-time is achieved via interactions between ARM computer. We apply Kernel extreme learning machine (K-ELM) algorithm as our after comparing four different...

Social network users often express their discontent with a product or service from company on social media. Such reaction is more pronounced in the aftermath of corporate scandal such as corruption food poisoning chain restaurant. In our work, we focus identifying negative purchase intent tweet, i.e. user not purchasing any consuming company. We develop binary classifier for task, which consists generalization logistic regression leveraging locality posts Twitter. conduct an extensive...

For a number of different formulations robust portfolio optimization, quadratic and absolute, we show that

This manuscript considers the design of an optimal FP (i.e., fixed-point) smoother for descriptor systems corrupted by delayed measurement and multiplicative noise. The observation equations are both additive noises. is presented in terms recursive mathematical based on standard singular value decomposition re-organized innovation analysis.

Optimal fixed-point smoothing problem for the descriptor systems with multiplicative noises is considered, where instantaneous and delayed observations are available. Standard singular value decomposition used to give restricted equivalent system, also include two different types of measurements. Reorganized innovation lemma projection theorem smoother system. The given in terms recursive Riccati equations.

The manipulator control model has the characteristics of high-order, nonlinear, multivariable and strong coupling, which makes it difficult for to have good adaptability autonomy. Aiming at problem poor reusability autonomy applications, a motion planning algorithm based on reinforcement learning is proposed. In this paper, continuous Actor-Critic applied increase environmental applicability manipulator, realize intelligent under simple kinematics modeling. At first, simulation environment...

Based on re-organization of innovation and the scalar weighting optimal information fusion criterion in minimum variance sense, time-delay Kalman filter is presented for linear discrete-time systems double models, each which includes instantaneous delayed sensors.

To overcome the weakness of generic neural networks (NNs) ensemble for prediction intervals (PIs) construction, a novel Map‐Reduce framework‐based distributed NN consisting several local Gaussian granular (GGNNs) is proposed in this study. Each network weighted according to its contribution model. The coefficient estimated by evaluating performance constructed PIs from each network. A new evaluation principle reported with consideration predicting indices. estimate modelling uncertainty and...

The optimal information fusion Kalman filter for wireless sensor network systems is studied. There are two subsystems, and the corresponding measurements from different channels, where system corrupted by multiplicative noises. Based on probability method scalar weighting criterion in minimum variance sense, networks with packet loss noises given.

Existing workload algorithms based on the Multiple Resources Theory (MRT) provide an effective approach for diagnosing operator overload caused by interference among concurrent tasks, however, their ability to handle in single task conditions is limited. We argue a time-based algorithm, developed Information Processing (IP) model of (Hendy, Liao, & Milgram, 1997), provides viable solution address this limitation. In study, we proposed new algorithmic implementation IP context network...