Data Fusion about Serviceability Reliability Prediction for the Long-Span Bridge Girder Based on MBDLM and Gaussian Copula Technique

This article presented a new data fusion approach for reasonably predicting dynamic serviceability reliability of the long-span bridge girder.Firstly,multivariate Bayesian dynamic linear model(MBDLM)considering dynamic correlation among the multiple variables is provided to predict dynamic extreme deflections;secondly,with the proposed MBDLM,the dynamic correlation coefficients between any two performance functions can be predicted;finally,based on MBDLM and Gaussian copula technique,a new data fusion method is given to predict the serviceability reliability of the long-span bridge girder,and the monitoring extreme deflection data from an actual bridge is provided to illustrated the feasibility and application of the proposed method.

A Novel Hidden Danger Prediction Method in CloudBased Intelligent Industrial Production Management Using Timeliness Managing Extreme Learning Machine

To prevent possible accidents,the study of data-driven analytics to predict hidden dangers in cloud service-based intelligent industrial production management has been the subject of increasing interest recently.A machine learning algorithm that uses timeliness managing extreme learning machine is utilized in this article to achieve the above prediction.Compared with traditional learning algorithms,extreme learning machine(ELM) exhibits high performance because of its unique feature of a high generalization capability at a fast learning speed.Timeliness managing ELM is proposed by incorporating timeliness management scheme into ELM.When using the timeliness managing ELM scheme to predict hidden dangers,newly incremental data could be added prior to the historical data to maximize the contribution of the newly incremental training data,because the incremental data may be able to contribute reasonable weights to represent the current production situation according to practical analysis of accidents in some industrial productions.Experimental results from a coal mine show that the use of timeliness managing ELM can improve the prediction accuracy of hidden dangers with better stability compared with other similar machine learning methods.

Accelerated Deterioration Mechanism and Reliability Evaluation of Concrete in Saline Soil Area

To reveal the deterioration mechanism and service life of concrete durability in the western saline soil area,the indoor accelerated test of the concrete specimen was simulated in the coupled environment of salt erosion and dry-wet cycles in the west saline soil area of China.The deterioration mechanism of concrete durability was revealed through the relative dynamic elastic modulus,relative quality evaluation parameters,SEM,and XRD evaluation indexes.Random Wiener distribution function was used for modeling life prediction.The results show that the relative dynamic elastic modulus evaluation parameter as an evaluation index of concrete durability under various environmental coupling effects is more reliable than the relative quality,there were holes and cracks in the concrete,and needle-like and layered crystals grow from the internal cracks.The corrosion products include ettringite,gypsum and other expansive crystals and non-gelling Mg(OH)_(2);the expansion stress caused by physical,chemical reaction,and temperature change under the action of drywet cycle aggravates the formation and development of cracks.The random Wiener distribution function can describe the degradation process of concrete specimen durability,and the established concrete reliability function can intuitively reflect the service life of concrete specimens.

A Time-Aware Dynamic Service Quality Prediction Approach for Services

Dynamic Quality of Service(QoS)prediction for services is currently a hot topic and a challenge for research in the fields of service recommendation and composition.Our paper addresses the problem with a Time-aWare service Quality Prediction method(named TWQP),a two-phase approach with one phase based on historical time slices and one on the current time slice.In the first phase,if the user had invoked the service in a previous time slice,the QoS value for the user calling the service on the next time slice is predicted on the basis of the historical QoS data;if the user had not invoked the service in a previous time slice,then the Covering Algorithm(CA)is applied to predict the missing values.In the second phase,we predict the missing values for the current time slice according to the results of the previous phase.A large number of experiments on a real-world dataset,WS-Dream,show that,when compared with the classical QoS prediction algorithms,our proposed method greatly improves the prediction accuracy.

QoS prediction algorithm used in location-aware hybrid Web service

Quality-of-Service （QoS） describes the non-functional characteristics of Web services. As such, the QoS is a critical parameter in service selection, composition and fault tolerance, and must be accurately determined by some type of QoS prediction method. However, with the dramatic increase in the number of Web services, the prediction failure caused by data sparseness has become a critical challenge. A new ＇hybrid user-location-aware prediction based on weighted Adamic-Adar （WAA）＇ （HUWAA） was proposed. The implicit neighbor search was optimized by incorporating location factors. Meanwhile, the ability of the improved algorithms to solve the data sparsity problem was validated in experiments on public real world datasets. The new algorithm outperforms the existing of item-based pearson correlation coefficient （IPCC）, user-based pearson correlation coefficient （UPCC） and Web service recommender system （WSRec） algorithms.

Durability problems of lining structures for Xiamen Xiang'an subsea tunnel in China

Durability problem of reinforced concrete for underground structures is a hot issue in the field of structural engineering. For underground structures, the prediction of structural service life and methodology for durability design are needed to estimate structural durability. Taking the case of Xiamen Xiang＇an subsea tunnel as background, which is designed to meet the requirement of lO0-year service life, the influential factors on tunnel lining durability are analyzed. Under the criteria of crack controlling and bearing capacity of linin~ structures, the theoretical service life of Xiamen Xiang＇an subsea tunnel lining is studied. The regulations, which are needed for the diffusion capability of chloride ions in concrete by the relevant diffusion tests, are proposed. After a quick corrosion test, the bearing capacity test on eccentric short columns is implemented to investigate the variation rules in the bearing capacity of models with time. Influence of the corrosion degree of steel bars on the bearing capacity of models is also investigated. Based on the results of model tests, the acceleration ratio between the quick corrosion in laboratory test and the natural corrosion environments is established. Thus, the natural service life of subsea tunnel lining structures can be obtained by means of laboratory tests. Then, the proposed method using this modified model is employed to predict the service life of tunnel lining structures. Finally, the design and construction measures for improving the durability of lining structures of subsea tunnel are introduced. The proposed method in the present study based on a real engineering project is superior to those with only theoretical assumptions, and would be more suitable for similar projects.

Privacy-preserving deep learning techniques for wearable sensor-based big data applications

Wearable technologies have the potential to become a valuable influence on human daily life where they may enable observing the world in new ways,including,for example,using augmented reality(AR)applications.Wearable technology uses electronic devices that may be carried as accessories,clothes,or even embedded in the user's body.Although the potential benefits of smart wearables are numerous,their extensive and continual usage creates several privacy concerns and tricky information security challenges.In this paper,we present a comprehensive survey of recent privacy-preserving big data analytics applications based on wearable sensors.We highlight the fundamental features of security and privacy for wearable device applications.Then,we examine the utilization of deep learning algorithms with cryptography and determine their usability for wearable sensors.We also present a case study on privacy-preserving machine learning techniques.Herein,we theoretically and empirically evaluate the privacy-preserving deep learning framework's performance.We explain the implementation details of a case study of a secure prediction service using the convolutional neural network(CNN)model and the Cheon-Kim-Kim-Song(CHKS)homomorphic encryption algorithm.Finally,we explore the obstacles and gaps in the deployment of practical real-world applications.Following a comprehensive overview,we identify the most important obstacles that must be overcome and discuss some interesting future research directions.

Experimental Investigation on Contribution of CFRP Attachment to Durability of Reinforced Concrete Structure Subjected to Chloride Attack

The function of externally-bonded carbon fiber reinforced polymer （CFRP） in preventing chloride from entering into concrete is verified by experiment. The results show that externally-bonded CFRP can be considered as a part of corrosion prevention system of strengthened concrete structures subjected to chloride ingress, and the contribution of CFRP should be considered in evaluation of durability of reinforced concrete structures with externally-bonded CFRP. With the effective shielding function of CFRP considered, an equation for residual lifetime prediction of concrete structures with externally-bonded CFRP is derived from Fick＇s dispersion law. CFRP has two functions for coastal concrete structures, including strengthening and increasing durability as part of corrosion prevention system.

A Semi-Mechanistic Model for Predicting the Service Life of Composite Coatings on VW63Z Magnesium Alloy

The application of Mg alloys is always accompanied by various coating technology, but a reliable model predicting the service life of coatings on Mg alloys is lacking but urgent. In this work, a semi-mechanistic model was proposed to predict the service life of plasma electrolytic oxidation (PEO) coating/electrophoretic coatings on a VW63Z Mg alloy;the model was decomposed into three parts: a first part depicting the degradation time of organic coating (L_(1)) and the diffusion time of electrolyte in the inorganic coating (L_(2)), respectively;a second part interpreting the breakdown of coatings due to the corrosion process (L_(3));a final part establishing an algorithm converting the accelerated tests into the real service environment (α);the effect of structural stress and dissimilar metal joints on the service life of coatings was also considered. Based on the ongoing accelerated experiments, the semi-mechanistic model could be able to predict the service life of both PEO coatings and composite coatings on VW63Z Mg alloy with a satisfiable precision.

Service behavior modeling and service behavior convergence-based radio resource scheduling in wireless systems

With the development of wireless networks, the amount of multiple services increased sharply in recent years. High quality multiple services with low price are urgently needed especially in new generation mobile communication systems, e.g., 3G/LTE networks. It is important to enhance the availability of data service resources. Services have strong association which are used by clients with similar behavior habits in networks. Such feature results in service behavior convergence （SBC） and its utilization will enhance resource efficiency. This paper proposes two applications of service behavior： service prediction and a scheduling algorithm which enhances bandwidth efficiency. Convergence cells are classified according to SBC and hot-spot services are broadcasted separately in each convergence cell. It is demonstrated by stimulation that the bandwidth is saved 80% more than classical cellular system and nearly 20% more than traditional broadcasting system.

A Method for Predicting Service Deprecation in Service Systems

An increasing number of web services are being invoked by users to create user applications（e.g.,mashups）. However, over time, a few good services in service systems have become deprecated, i.e., the service is initially available and is invoked by service users, but later becomes unavailable. Therefore, the prediction of service deprecation has become a key issue in creating reliable long-term user applications. Most existing research has overlooked service deprecation in service systems and has failed to consider long-term service reliability when making service recommendations. In this paper, we propose a method for predicting service deprecation, which comprises two components： Service Comprehensive Feature Modeling（SCFM） for extracting service features relevant to service deprecation and Deprecated Service Prediction（DSP） for building a service deprecation prediction model. Our experimental results on a real-world dataset demonstrate that our method yields an improved Area-Under-the-Curve（AUC） value over existing methods and thus has better accuracy in service deprecation prediction.