The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy. However, older ideas about privacy may well remain valid and useful. This note reviews two recent works on privacy in the light of the wisdom of some of the early literature, in particular the principles distilled by...
Aiming at the accurate prediction of APU residual life in civil aviation, Fusion of historical state performance monitoring data, a method of APU residual life prediction based on proportional hazards model (PHM) is proposed. This method first gives a life prediction algorithm based on PHM. Then, based on the historical performance degradation data and historical failure time data, the genetic parameters...
In the field of defense science and technology, some long-life and high-reliability products cost a lot to carry out reliability test, including life test, degradation test and enhancement test. Thus, a more effective product testing and data analysis method are expected. Reliability enhancement test (RET) is commonly employed to improve products reliability, whose data is usually utilized to determine...
Unsupervised learning is a good neural network training way. However, the unsupervised learning algorithm is rare. The generative model is an interesting algorithm which can generate the similar data as the sample data by building a probabilistic model of the input data, and it can be used for unsupervised learning. Variational autoencoder is a typical generative model which is different from common...
Rapid pace of global urbanization has posed significant challenges to urban transportation infrastructures. Existing urban transit systems suffer many well-known shortcomings, where public transits have limits on coverage areas, and fixed schedules, and private transits are expensive and fail to timely meet the demand needs. We thus envision a Cloud-Commuting system, that employs a giant pool of centralized...
Understanding the semantic relations between vision and language data has become a research trend in artificial intelligence and robotic systems. The lack of training data is an essential issue for vision-language understanding. We address the problem of image and sentence cross-modal retrieval when paired training samples are not sufficient. Inspired by recent works in variational inference, in this...
Autoencoder is an excellent unsupervised learning algorithm. However, it can not generate kinds of sample data in the decoding process. Variational autoencoder is a typical generative adversarial net which can generate various data to augment the sample data. In this paper, we want to do some research about the information learning in hidden layer. In the simulation, we compare the hidden layer learning...
To assimilate satellite-based passive microwave observation over heavy clouds and precipitation into numerical weather prediction (NWP) systems and thus to improve the performance of it has become an intensely studied topic. These attempts rely on the development of a radiative transfer (RT) model that accounts for particle scattering and accurately simulates the observation process at an acceptable...
Spark has grown both in popularity and complexity in recent years. In order to use available resources in an efficient way, users need to understand how the behavior of their applications is affected by the size of the datasets and various configuration settings. Indeed, Spark allows users to specify many configuration parameters and understanding the impact of these choices with respect to the application...
Convolutional Neural Network (CNN) is a kind of deep artificial neural network. CNN has kinds of merits, such as multidimensional data input, and fewer parameters. However, the network always has the problem of overfitting due to lots of connection in the full connection layer. In order to overcome the overfitting problem, the denoising method is used to corrupt input data and hidden unit output which...
In this paper, we present the design and implementation of a model-driven auto scaling solution for Hadoop clusters. We first develop novel performance models for Hadoop workloads that relate job completion times to various workload and system parameters such as input size and resource allocation. We then employ statistical techniques to tune the models for specific workloads, including Terasort and...
This paper proposes a dynamic nonlinear autoregressive model based algorithm for gene regulatory networks (GRNs) identification with biological stage change detection using the L1-regularization. This allows subtle variations in the same state to be penalized and prominent changes across adjacent states to be captured. Furthermore, by assuming local-stationarity within each detected biological state,...
Patient flow, on one hand, represents the progression of a patient's health status; on the other hand, can be thought of the transferring of patients through multiple hospital units within a hospital or among different hospitals. Furthermore, patient flow, in the aggregate, is equivalent to the demand for health care services. Thus, patient flow management is of great importance to monitor and control...
With rapid growth in smart phones and mobile data, effectively managing cellular data networks is important in meeting user performance expectations. However, the scale, complexity and dynamics of a large 3G cellular network make it a challenging task to understand the diverse factors that affect its performance. In this paper we study the RNC (Radio Network Controller)-level performance in one of...
With the rapid growth of data in various domains, models for data processing become more and more complicated and require higher and higher computing power of local machines. In our opinion, it is a good solution to put models into the "cloud". Integrating and categorizing these models in different domains is convenient for users. They don't have to establish similar systems for different...
It is well known that the variability model, which captures the commonality and variability of the software product families, is very important to the software product line. Current software product line variability modeling methods relies on the analysis ability of the domain analysts heavily. When the single system of product families is large, it will be difficult to establishing the variability...
Higher-order Singular Value Decomposition (HOSVD) for tensor decomposition is widely used in multi-variate data analysis, and has shown applications in several areas in computer vision in the last decade. Conventional multi-linear assumption in HOSVD is not translation invariant — translation in different tensor modes can yield different decomposition results. The translation is difficult to remove...
In this thesis, we propose a skin color detection algorithm based on adaptive model and design Gaussian classifier. Confirm face according to the geometric relationship of face features and organs. To raise the detection rate, we use the mosaic rules to make a further verification. Experimental results show that the method we put forward can detect the facial area correctly.
When auditing the large enterprise groups with many accounting subjects, in order to find. the doubtful auditing points quickly in the mass electronic data, we designed and developed a accounting report procedure for single subject according to the logic of balance sheet with the parallel simulation; adopted the associative rules to mine the audit features of electronic data, and combined with the...
Conventional risk assessments in Ad-Hoc Networks always require sample satisfy specific distribution with large quantity and establish models through subjective judgment, these methods lack general applicability, objectivity and credibility. Moreover, some models only focus on single time point evaluation and failed to thoroughly reveal dynamic behavioral character. To solve these problems and make...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.