Reliability Prediction Approach Research Articles

A Study of Incorporation of Deep Learning Into Software Reliability Modeling and Assessment

Software is widely used in many application domains. The most popular software are used by millions every day. How to accurately predict and assess the reliability of developed software is becoming increasingly important for project managers and developers. Previous studies have primarily used the software reliability growth model (SRGM) to evaluate and predict software reliability, but prediction results cannot be accurate at particular times or in particular situations. One of the main reasons is that simplified assumptions and abstractions are usually made to simplify the problem when developing SRGMs. Selecting an appropriate SRGM should depend on the key characteristics of the software project. In this article, we propose a deep learning-based approach for software reliability prediction and assessment. Specifically, we clearly demonstrate how to derive mathematical expressions from the computational methods of deep learning models and how to determine the correlation between them and the mathematical formula of SRGMs, and then, we use the back-propagation algorithm to obtain the SRGM parameters. Furthermore, we further integrate some deep learning-based SRGMs and also propose a method for the weighted assignment of combinations. Three real open source software failure datasets are used to evaluate the performance of the proposed models compared to selected SRGMs. The experimental results reveal that our proposed deep learning-based models and their combinations perform better than several classical SRGMs.

Identification of surrogates for rapid monitoring of microbial inactivation by ozone for water reuse: A pilot-scale study

The complex contaminants in reclaimed water sources and delayed feedback of microbial detection have brought tremendous challenges to disinfection process control. The identification of sensitive and online surrogates for indicating microbial inactivation efficacy is vital to evaluate and optimize the disinfection technologies and processes. This study analyzes the inactivation of microbial indicators during ozone disinfection at a pilot-scale study over 5 months. It is identified that total fluorescence (TF) intensity, ultraviolet absorbance at 254 nm (UV254) and intracellular adenosine triphosphate (cATP) concentration can act as surrogates in predicting microbial inactivation by ozone. Particularly, the empirical linear correlations for log removal values (LRV) of TF, UV254 and cATP concentration are developed for the inactivation of four widely applied microbial indicators, namely the total coliforms, fecal coliforms, Escherichia coli (E. coli) and heterotrophic plate count (HPC) (R2 = 0.86–0.96). Validation analyses are further conducted to verify the robustness and effectiveness of empirical models. Notably, TF is considered as the most efficient surrogate due to its high sensitivity, accuracy and reliability, whereas cATP concentration is an efficient supplement to directly reflect total microbial counts. The study is important to provide a rapid and reliable approach for ozone disinfection efficiency evaluation and prediction.

Simple Approach for Reliable Prediction of the Flash Point of Organosilicon Compounds as Compared to the Best Available Methods

Simple Approach for Reliable Prediction of the Flash Point of Organosilicon Compounds as Compared to the Best Available Methods

Bootstrap aggregation ensemble learning-based reliable approach for software defect prediction by using characterized code feature

Bootstrap aggregation ensemble learning-based reliable approach for software defect prediction by using characterized code feature

Plant Leaf Disease Detection by Using Different Classification Techniques: Comparative

One of the main factors that assist to increase the growth of any country is Agriculture. The detection of diseases from plant leaf images is one of the most important fields of agricultural research. To identify disease factors, this field requires a reliable prediction approach. Data Mining (DM) is the process of analyzing data from different aspects and summarizing it into valuable information. It helps users to categorize and identify relationships between data from various dimensions. As there are many plants on the farm, detecting and classifying the diseases of each plant on the farm is extremely difficult for the human eye. And diagnosing each plant is very critical since these diseases may spread. DM classification is an important method that has a wide range of applications. It classifies each item in a set of data into one of a set of predefined classes. In this paper, a comparison of different DM classification methods such as Naive Bayes, Decision trees, SVM, and Random Forest algorithms has been illustrated by using of Weka Tool.

In Vitro Hepatic Uptake in Human and Monkey Hepatocytes in the Presence and Absence of Serum Protein and Its In Vitro to In Vivo Extrapolation.

It is well documented that human hepatic clearance based on in vitro metabolism or transporter assays systematically resulted in underprediction; therefore, large empirical scalars are often needed in either static or physiologically based pharmacokinetic (PBPK) models to accurately predict human pharmacokinetics (PK). In our current investigation, we assessed hepatic uptake in hepatocyte suspension in Krebs-Henseleit buffer in the presence and absence of serum. The results showed that the unbound intrinsic active clearance (CLu,int,active) values obtained by normalizing the unbound fraction in the buffer containing 10% serum were generally higher than the CLu,int,active obtained directly from protein free buffer, suggesting "protein-facilitated" uptake. The differences of CLu,int,active in the buffer with and without protein ranged from 1- to 925-fold and negatively correlated to the unbound serum binding of organic anion transporting polypeptide substrates. When using the uptake values obtained from buffer containing serum versus serum-free buffer, the median of scaling factors (SFs) for CLu,int,active reduced from 24.2-4.6 to 22.7-7.1 for human and monkey, respectively, demonstrating the improvement of in vitro to in vivo extrapolation in a PBPK model. Furthermore, values of CLu,int,active were significantly higher in monkey hepatocytes than that in human, and the species differences appeared to be compound dependent. Scaling up in vitro uptake values derived in assays containing species-specific serum can compensate for the species-specific variabilities when using cynomolgus monkey as a probe animal model. Incorporating SFs calibrated in monkey and together with scaled in vitro data can be a reliable approach for the prospective human PK prediction in early drug discovery. SIGNIFICANCE STATEMENT: We investigated the protein effect on hepatic uptake in human and monkey hepatocytes and improved the in vitro to in vivo extrapolation using parameters obtained from the incubation in the present of serum protein. In addition, significantly higher active uptake clearances were observed in monkey hepatocytes than in human, and the species differences appeared to be compound dependent. The physiologically based pharmacokinetic model that incorporates scaling factors calibrated in monkey and together with scaled in vitro human data can be a reliable approach for the prospective human pharmacokinetics prediction.

Prediction of transient wellbore cement circulating temperature distribution using CFD simulation

Accurate prediction of the cement slurry temperature while being circulated downhole is critical for a successful cement job. Failure to predict the cement slurry temperature correctly may result in premature or delayed cement setting. Due to the practical limitations of using temperature sensors for direct measurement and the complexity of the bottomhole circulating conditions, it is difficult to gather accurate information about how the temperature of cement slurry changes as it is being circulated through the well. To overcome these challenges and help with designing a cement system more accurately, a computational fluid dynamics (CFD) model is developed. The model simulates the balanced-plug cementing operation, which considers the continuous displacement of the drilling fluid by the cement slurry and the cement slurry by water. The CFD model predicts the transient changes in the temperatures of the cement slurry and near wellbore formation during this displacement process involving three different fluids. A new dynamic mesh method was developed to effectively handle the interface mixing of different fluids, and thus model the three-fluid displacement process in the annulus more realistically. The CFD model can also deal with complex well conditions such as deviated wellbores, variable geothermal gradients and formation rock properties. Most importantly, in the absence of the measurements allowing direct monitoring of the downhole conditions, the new CFD model allows for continuous monitoring of downhole transient fluid and formation temperature at any position along the wellbore. The results of CFD transient simulations indicate that the bottomhole circulation temperature (BHCT) values predicted by using API method are significantly overestimated. The highest cement slurry temperature in the annulus was observed at some distance above the bottom of the well. Results also confirmed the existence of an equilibrium plane (extending horizontally) into the formation across which a temperature reversal was observed. The formations above and below the equilibrium plane have opposite heat transfer patterns. The depth of the equilibrium plane rises steadily while its temperature gradually decreases as the circulation continues. The change of the cement/drilling fluid interface temperature is traced dynamically. CFD simulation is proven to be a realistic and reliable approach for prediction of the cement circulating temperature and can be easily used in combination with real time operational data. Practical guidelines and solutions derived from the simulation results can be useful for improved cement job design in field applications.

Conditional generative adversarial network model for simulating intensity measures of aftershocks

Earthquake disaster records demonstrate that the influence of aftershocks (ASs) needs to be considered in structural seismic design and performance assessment, owing to the additional damage caused by them. To study the failure mechanism of a structure undergoing a sequence earthquake (i.e., mainshock–aftershock (MS–AS)), a clear understanding of the correlation between the intensity measures (IMs) of an MS–AS is important. However, the above correlation has not yet been systematically studied. Previously, some researchers have investigated the correlation between the individual IMs of an MS–AS separately by a Copula function based on an assumption that all the IMs of the MS (AS) are independent. However, the IMs are actually related, owing to their definition. Concurrently, deep learning (particularly the generation models) can be used to reveal the potential connections between data without any assumptions. Moreover, these models can present the conditional probability distribution of data by adding specific conditions. This study aims to build a conditional generative adversarial network (CGAN) model to simulate the IMs of an AS of an MS–AS, which can not only reflect the correlation between the corresponding IMs of the MS–AS but also that between the IMs used. The performance of this model is ascertained based on residual analysis, and the IM AS predictability is tested using real records. This study selects 972 MS–AS ground motions from the Next Generation Attenuation-West2 (NGA-West2) database, randomly dividing them into 80% and 20% and using as the training set and testing set, respectively. The results show that the CGAN model can predict the IMs of ASs with good accuracy. Moreover, the ground motion prediction equation (GMPE) by Abrahamson et al. (ASK14) is selected to compare with the CGAN model, and it is exhibited that the CGAN model matches the as-recorded IMs of ASs better that the former. All these results demonstrate that the proposed CGAN model is a promising and reliable approach for IM prediction of an AS.

Spatial Variability of Grouting Layer of Shield Tunnel and Its Effect on Ground Settlement

This study aims to investigate the effect of the spatial variability of grouting-layer thickness on ground-surface settlement caused by shield tunneling and to provide a rational prediction method. The spatial characteristics of grouting layers were obtained based on statistical analysis. The random finite element method was used to study the effect of spatial variability of different parameters on ground-surface settlement. Simulation results indicate that the spatial variability of the grouting layer has a negative impact on ground settlement. The surface settlement will be underestimated without considering the spatial characteristics of the grouting layer. Thus, a reliable prediction approach of the maximum ground settlement was proposed to control the construction quality.

Implementation of data intelligence models coupled with ensemble machine learning for prediction of water quality index.

In recent decades, various conventional techniques have been formulated around the world to evaluate the overall water quality (WQ) at particular locations. In the present study, back propagation neural network (BPNN) and adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), and one multilinear regression (MLR) are considered for the prediction of water quality index (WQI) at three stations, namely Nizamuddin, Palla, and Udi (Chambal), across the Yamuna River, India. The nonlinear ensemble technique was proposed using the neural network ensemble (NNE) approach to improve the performance accuracy of the single models. The observed WQ parameters were provided by the Central Pollution Control Board (CPCB) including dissolved oxygen (DO), pH, biological oxygen demand (BOD), ammonia (NH3), temperature (T), and WQI. The performance of the models was evaluated by various statistical indices. The obtained results indicated the feasibility of the developed data intelligence models for predicting the WQI at the three stations with the superior modelling results of the NNE. The results also showed that the minimum values for root mean square(RMS) varied between 0.1213 and 0.4107, 0.003 and 0.0367, and 0.002 and 0.0272 for Nizamuddin, Palla, and Udi (Chambal), respectively. ANFIS-M3, BPNN-M4, and BPNN-M3 improved the performance with regard to an absolute error by 41%, 4%, and 3%, over other models for Nizamuddin, Palla, and Udi (Chambal) stations, respectively. The predictive comparison demonstrated that NNE proved to be effective and can therefore serve as a reliable prediction approach. The inferences of this paper would be of interest to policymakers in terms of WQ for establishing sustainable management strategies of water resources.

Bayesian regression based condition monitoring approach for effective reliability prediction of random processes in autonomous energy supply operation

The probabilistic analysis on condition monitoring data has been widely established through the energy supply process to specify the optimum risk remediation program. In such studies, the fluctuations and uncertainties of the operational data including the variability between source of data and the correlation of observations, have to be incorporated if the efficiency is of importance. This study presents a novel probabilistic methodology based on observation data for signifying the impact of risk factors on safety indicators when consideration is given to uncertainty quantification. It provides designers, risk managers and operators a framework for risk mitigation planning within the energy supply processes, whilst also assessing the online reliability. These calculations address the involved and, most of the time, unconsidered risk to make a prediction of safety conditions of the operation in future. To this end, the generalized linear model (GLM) is applied to offer the explanatory model as a regression function for risk factors and safety indicators. Hierarchical Bayesian approach (HBA) is then inferred for the calculations of regression function including interpretation of the intercept and coefficient factors. With Markov Chain Monte Carlo simulation from likelihood function and prior distribution, the HBA is capable of capturing the aforementioned fluctuations and uncertainties in the process of obtaining the posterior values of the intercept and coefficient factors. To illustrate the capabilities of the developed framework, an autonomous operation of Natural Gas Regulating and Metering Station in Italy has been considered as case study.

Analysis of flexible pavement with cross-anisotropic material properties

Presently, there is a sway from empirical approaches to mechanistic-empirical based methods for pavement design, in which mechanistic pavement responses are related to the pavement performance. It provides a more rational approach for reliable prediction of the pavement distresses and pavement life. In mechanistic analysis, the materials are usually considered as linear elastic and isotropic, which is not realistic and rather exhibit a more complex behaviour. Finite element modelling (FEM) has the ability to handle this complex material properties, however it is time consuming and also needs expertise in this area. Therefore, multilayered linear elastic theory based programs are still favoured over FEM for analysis of flexible pavements. Most of the pavement materials (specifically the unbound materials) are anisotropic, however can be approximated as cross-anisotropic (different properties in vertical and horizontal directions) material. In this study, a multilayered linear elastic theory based program ‘CrossPave’ has been developed, which is capable of considering the cross-anisotropic behavior of the pavement materials. Through a comparison between isotropic and cross-anisotropic analysis of pavements, this study shows that isotropic analysis underestimates and some case overestimates the mechanistic parameters that may lead to incorrect pavement lives.

A robust reliability prediction method using Weighted Least Square Support Vector Machine equipped with Chaos Modified Particle Swarm Optimization and Online Correcting Strategy

Accurate reliability prediction in engineering systems has drawn more and more attention over the past decades due to its important role in accessing the security condition of the system and providing safety operation basis, however, which still remains challenging caused by the mismatch of reliability prediction model especially for dynamic uncertainty of future sampled data. Therefore, a novel approach for reliability prediction with an optimal Online Correcting Strategy (OCS) combined with Weighted Least Square Support Vector Machine (WLSSVM) and Chaos Modified Particle Swarm Optimization (CMPSO) algorithm, named OCS–CMPSO–WLSSVM, are proposed, where WLSSVM models the functional relationship between input and output of the system, CMPSO optimizes the parameters of WLSSVM, and OCS modifies the model to reduce its mismatch as the system runs, respectively. The performance of the proposed model is demonstrated with five classic practical engineering examples and compared with the existing methods reported in literature in detail. The experimental results show that the proposed method not only has higher reliability prediction accuracy and robustness, but also has its superiority and applicability in other fields including time-ordered, feature-based regression problem and classification problem.

Data analytics approach for travel time reliability pattern analysis and prediction

Travel time reliability (TTR) is an important measure which has been widely used to represent the traffic conditions on freeways. The objective of this study is to develop a systematic approach to analyzing TTR on roadway segments along a corridor. A case study is conducted to illustrate the TTR patterns using vehicle probe data collected on a freeway corridor in Charlotte, North Carolina. A number of influential factors are considered when analyzing TTR, which include, but are not limited to, time of day, day of week, year, and segment location. A time series model is developed and used to predict the TTR. Numerical results clearly indicate the uniqueness of TTR patterns under each case and under different days of week and weather conditions. The research results can provide insightful and objective information on the traffic conditions along freeway segments, and the developed data-driven models can be used to objectively predict the future TTRs, and thus to help transportation planners make informed decisions.

Prediction of Propeller Performance Using Computational Fluid Dynamics Approach

A reliable prediction approach to obtain a sufficient thrust and torque to propel the ship at desired forward speed is obviously required. To achieve this objective, the authors propose to predict the thrust coefficient (KT), torque coefficient (KQ) and efficiency (η) of the propeller in open-water model test condition using Computational Fluid Dynamics (CFD) simulation approach. The computational simulation presented in the various number of rotational speed (RPM) within the range of advance ratio J=0.1 up to 1.05. The higher value of J lead to decrease 10KQ and KT. While the η increased steadily at the lower value of J and decreased at the higher value of J. The results also showed that the propeller with 1048 rpm obtain a better efficiency at J=0.95 with η= 88.25%, 10KQ=0.1654 and KT= 0.0942. The computation result is very useful as preliminary data for propeller performance characteristics.

A reliable traffic prediction approach for bike‐sharing system by exploiting rich information with temporal link prediction strategy

AbstractBike‐sharing systems have been widely used in major cities across the world. As bike borrowing and return at different stations in different periods are not balanced, the bikes in a bike‐sharing system need to be redistributed frequently to rebalance the system. Therefore, traffic flow forecasting of the bike‐sharing system is an important issue, as this is conducive to achieving rebalancing of the bike system. In this article, we present a new traffic flow prediction approach based on the temporal links in dynamic traffic flow networks. A station clustering algorithm is first introduced to cluster stations into groups. A temporal link prediction method based on the dynamic traffic flow network method (STW+M) is then proposed to predict the traffic flow between stations. In our method, the non‐negative tensor decomposition and time‐series analysis model capture the rich information (temporal variabilities, spatial characteristics, and weather information) of the across‐clusters transition. Then, a temporal link prediction strategy is used to forecast potential links and weights in the traffic flow network by investigating both the network structure and the results of tensor computations. In order to assess the methods proposed in this article, we have used the data of bike‐sharing systems in New York and Washington, DC to conduct bike traffic prediction and the experimental results have shown that our method produces the lowest root mean square error (RMSE) and mean square error (MSE). Compared to four prediction methods from the literature, our RMSE and MSE of the two datasets have been lowered by an average of 2.55 (Washington, DC) and 2.41 (New York) and 3.35 (Washington, DC) and 2.96 (New York), respectively. The results show that the proposed approach improves predictions of traffic flow.

Survey of combined hardware–software reliability prediction approaches from architectural and system failure viewpoint

Apart from hardware and software-specific failures, failures arising from hardware–software interaction causes notorious system failures. Researches have reported two types of interaction failures in a system: hardware-driven software failure and software-driven hardware failure. An efficient reliability prediction approaches must consider all types of interactions. We critically analyse the existing reliability prediction models for the combined hardware–software system. We also propose a comparison framework to evaluate the existing reliability models for combined hardware–software systems. The results of our study suggest that none of the considered approaches completely satisfy the characteristics of a good reliability prediction model. Existing approaches hardly consider all types of hardware–software interactions. They also fail to consider reliability aspects of distributed systems where a system interacts with external devices. Our proposed comparison framework can be used as a benchmark to construct an efficient reliability prediction model for combined hardware–software systems.

A personalized clustering-based and reliable trust-aware QoS prediction approach for cloud service recommendation in cloud manufacturing

With the growing popularity of cloud manufacturing (CMfg), an increasing number of functionally equivalent cloud services are available on the Internet, which makes cloud service recommendation an important topic recently. Since the quality-of-service (QoS) varies largely in cloud environment, many Collaborative Filtering (CF) approaches are recently proposed to predict the uncertain QoS by utilizing the historical QoS records of similar users. In addition to the data sparsity problem, however, most existing approaches also ignore the task similarity among different users, while dissimilar tasks requested by similar users may lead to quite different QoS prediction results, and thus cannot achieve higher prediction accuracy and recommendation quality. To address this problem, we develop a novel clustering-based and trust-aware approach. Firstly, a set of similar users can be identified from the view of task similarity using clustering-based algorithm, where task similarity can be computed by incorporating both explicit textual information and rating information as well as implicit context information. Secondly, considering the fact that the QoS values may be contributed by unreliable users, we design a trust-aware CF approach by merging local and global trust values, to reconstruct trust network of the clustered users. Finally, we combine the clustering-based algorithm and trust-aware approach to make a more personalized QoS prediction and reliable cloud service recommendation for the active user in CMfg. Experimental results on two real-world data sets demonstrate the effectiveness of the proposed approach compared with other state-of-the-art approaches.

A reliable regression-based approach for seismic reservoir characterization

ABSTRACTSeismic reservoir characterisation includes seismic inversion and property prediction which provides valuable information from seismic data. A good reservoir characterisation workflow requires a reliable seismic inversion method. The most common and reliable approach for reservoir property prediction from surface seismic data is rock physics in which a physical or empirical model is used to describe the properties. However, these models require a huge number of predefined constant parameters, which makes their use complicated in practice. To overcome this, we propose a simple regression-based methodology to estimate reservoir properties (including porosity, water saturation and shale volume) from the elastic properties. The proposed methodology is a modified version of Lambda-Mu-Rho analysis for regression of water saturation and shale volume estimations. To find the elastic properties, we use Bayesian linearised amplitude versus offset inversion. Both the inversion method and the proposed methodology for seismic reservoir characterisation provide reliable information that correlates very well with the well data. Compared with the rock physics method, which is complicated and requires a number of parameters, the proposed methodology is straightforward and easy to apply.

A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes

Directed evolution is an important research activity in synthetic biology and biotechnology. Numerous reports describe the application of tedious mutation/screening cycles for the improvement of proteins. Recently, knowledge-based approaches have facilitated the prediction of protein properties and the identification of improved mutants. However, epistatic phenomena constitute an obstacle which can impair the predictions in protein engineering. We present an innovative sequence-activity relationship (innov’SAR) methodology based on digital signal processing combining wet-lab experimentation and computational protein design. In our machine learning approach, a predictive model is developed to find the resulting property of the protein when the n single point mutations are permuted (2n combinations). The originality of our approach is that only sequence information and the fitness of mutants measured in the wet-lab are needed to build models. We illustrate the application of the approach in the case of improving the enantioselectivity of an epoxide hydrolase from Aspergillus niger. n = 9 single point mutants of the enzyme were experimentally assessed for their enantioselectivity and used as a learning dataset to build a model. Based on combinations of the 9 single point mutations (29), the enantioselectivity of these 512 variants were predicted, and candidates were experimentally checked: better mutants with higher enantioselectivity were indeed found.