Approach For Quality Prediction Research Articles

A water quality prediction approach for the Downstream and Delta of Dongjiang River Basin under the joint effects of water intakes, pollution sources, and climate change

Water quality prediction is an important means for scientific water environment management and early warning measures. However, its reliability is often restricted by the uncertainties of parameters and pollution sources. Previous methods for resolving these uncertainties still have shortcomings due to low computational efficiency and incomplete coverage of mechanisms. With insufficient data, they also overlooked revealing the comprehensive impact of water intakes, pollution sources, and climate change on water quality in river networks. Insight understanding migration law and the main driving mechanisms under these factors is crucial for water resources and sustainable socioeconomic development. Here, we developed an efficient multi-scenario ensemble water quality prediction (MEWQP) approach to address the deficiency. The Downstream and Delta of Dongjiang River Basin was the demonstrative case. Firstly, we developed multiple parameters and pollution sources inverse estimation method by incorporating the Water Quality Analysis Simulation Program (WASP), general likelihood uncertainty estimation, and inverse methods to improve accuracy. Secondly, the Markov-Chain was used to predict flows affected by climate change. Thirdly, 60 scenarios were analyzed to quantify the impacts of multiple factors on water quality including 5-day biochemical oxygen demand (BOD5), ammonia nitrogen (NH3-N), and dissolved oxygen (DO), and identify an optimized scheme of water intakes. Results show that: (1) WASP has good performance for BOD5, NH3-N, and DO with Mean Absolute Relative Error of 5.87%, 9.19%, and 15.25%, respectively; (2) pollution sources have the greatest impact, followed by extreme climate and intakes. Their combined impacts are greater than individuals; (3) under non-water intakes DO can be improved by 31%, also offset the impact of climate change by 16%; (4) the optimized scheme of intakes could improve DO by 6%. Therefore, decision-makers should simultaneously adjust water intake and reduce pollution sources to obtain high-quality water resources.

Small-batch product quality prediction using a novel discrete Choquet fuzzy grey model with complex interaction information

With manufacturing focused on multi-variety and small-batch intelligent production, the challenge is to guarantee and ensure good product quality. This paper proposes a novel small-batch product quality prediction approach considering complex interaction information. In this paper, first, to handle the complex nonlinear correlations among the manufacturing process variables, a kernel principal components analysis is used to extract the major features from the high-dimensional data. Second, we combine the discrete multivariate grey model and generalized discrete Choquet fuzzy integral to propose a discrete Choquet fuzzy grey model so as to capture the complex interaction information among the process variables. Next, an adjoint sensitivity analysis is applied to characterize the changes in the process variables on the predicted product quality index. We conduct an experiment on six semiconductor products made in China to validate the proposed model against a library of nine other methods. Our model yields an average reduction of 11.02% on MAPE, 20.47% on MSE, 13.56% on STD, and an average increase of 46.37% on EVS for six types of products. Our results inform that the proposed model is suitable for predicting manufacturing product quality when the process variables interact significantly, and we can prioritize the process variables for remedial action accordingly.

Data Augmentation-Based Manufacturing Quality Prediction Approach in Human Cyber-Physical Systems

Abstract The vigorous development of the human cyber-physical system (HCPS) and the next generation of artificial intelligence provide new ideas for smart manufacturing, where manufacturing quality prediction is an important issue in the manufacturing system. However, the small-scale data from humans in emerging HCPS-enabled manufacturing restrict the development of traditional quality prediction methods. To address this question, a data augmentation-based manufacturing quality prediction approach in human cyber-physical systems is proposed in this paper. Specifically, a Data Augmentation-Gradient Boosting Decision Tree (DA-GBDT) model is developed for quality prediction under the HCPS context. In addition, an adaptive selection algorithm of data augmentation rate is designed to balance the trade-off between the training time of the prediction model and the prediction accuracy. Finally, the experimental results of automobile covering products demonstrate that the proposed method can improve the average prediction error of the model compared with the prevailing quality prediction methods. Moreover, the predicted quality information can provide guidance for product optimization decisions in smart manufacturing systems.

A new approach for quality prediction and control of multistage production and manufacturing process based on Big Data analysis and Neural Networks

As consumers care more and more about product quality, it is important to mine the deep correlations between production and manufacturing parameters and the evaluation of product quality through the analysis of industrial big data. The existing research of product quality prediction faces several major problems: the lack of diverse quality features, the poor tractability of abnormal parameters, the strong nonlinearity of parameters, the obvious sequential property of data, and the severe time lag of data. To solve these problems, this paper explores the quality prediction and control of multistage MP process (MPMP) based on big data analysis. Firstly, the prediction strategy and flow were specified for MPMP product quality prediction, and the features were extracted from MPMP product quality. After that, the MPMP product quality features were described in multiple dimensions, the attention mechanism was introduced to the prediction process. In addition, the recurrent neural network was improved, and an MPMP product quality prediction model was established on bidirectional long short-term memory (BiLSTM) network. Our model was compared with AdaBoost and XGBoost through experiments. The effectiveness of our model was demonstrated by the results of the appearance quality PQ1, and the area under the curve (AUC) for each process parameter. In general, our model is superior to other algorithms in the accuracy, mean accuracy, and precision of product quality prediction.

Wireless Resource Scheduling for High Mobility Scenarios: A Combined Traffic and Channel Quality Prediction Approach

The rapid growth of mobile data traffic in a high-speed scenario imposes great challenges on wireless system design and optimization, where the inherent Doppler shift, frequent cell switching, and large penetration loss will significantly degrade the quality of transceiver signals. Wireless resource scheduling dynamically allocates wireless resources according to the user channel conditions and quality of service requirement, which is an enabling approach to maximize the resource utilization. In this paper, we develop a new wireless resource scheduling method in high mobility scenario to uplift the system performance. We first propose a feature extraction algorithm to extract the spatial traffic characteristics. On this basis, several time-series prediction algorithms are leveraged to predict the traffic volume. Then, we introduce cell switching indicator (CSI) into channel quality prediction to improve the signal-to-noise ratio (SNR) prediction performance. Based on the predicted results of service traffic and user channel quality variations, a resource scheduling strategy is proposed, which compromises the total system throughput and user satisfaction. Simulation results validate the effectiveness of the proposed scheduling algorithm.

Dual-Channel Multi-Task CNN for No-Reference Screen Content Image Quality Assessment

Nowadays the problem of image quality assessment (IQA) for screen content images (SCIs) has become a research hotspot as they are ubiquitous in multimedia applications. Although the quality assessment of natural images (NIs) has been continuously developed in the past few decades, few NI-oriented IQA methods can be directly applied on SCIs due to different visual characteristics between them. In this paper, we present a no-reference quality prediction approach considering the content information of SCIs, which is based on dual-channel multi-task convolutional neural network. First, we segment a SCI into small patches and classify them as the textual patches and the pictorial patches. Then, we devise a novel dual-channel convolutional neural network (CNN) to predict the quality of textual patches and pictorial patches. Finally, we propose an effective adaptive weighting strategy for quality score aggregation. The proposed CNN is built on an end-to-end multi-task learning framework, which assists the SCI quality prediction task through the histogram of oriented gradient (HOG) feature prediction task to learn a better mapping between the input patch and its quality score. The adaptive weighting strategy further improves the representation ability of each SCI patch. Experimental results on two largest SCI-oriented databases demonstrate that the proposed method outperforms most of the state-of-the-art no-reference IQA methods and the full-reference IQA methods.

Evaluation and modeling of automotive transmission whine noise quality based on MFCC and CNN

The sound quality of automotive transmission noise strongly influences passengers’ psychological and physiological perceptions. To predict the sound quality of automotive transmission noise, a uniform deceleration noise test with two automotive transmissions has been conducted in a semi-anechoic room. All recorded transmission noise signals have been divided into 5 s segments and subsequently evaluated subjectively through the rating scales test by a jury. In addition, a novel prediction method, namely, Mel-Frequency Cepstral Coefficients-based convolutional neural networks (MFCC-CNN), which substitute the softmax classification layer for the linear transform prediction layer at the output of the general CNN’s structure and take MFCC feature map as input, has been proposed to predict the transmission sound quality. MFCC's distinguishing performance on sound quality has been validated. The parameter selection of the MFCC-CNN model has been compared and studied using a grid search. In addition, three conventional machine-learning-based methods have been introduced to enable a comparison of the performance with the newly developed MFCC-CNN. The results show the following: (1) In different transmission gears, MFCC features can distinguish different sound quality noises. (2) The accuracy of the proposed MFCC-CNN sound quality prediction approach are better than those of the 3 other referenced methods. (3) The correlation coefficient of prediction value from MFCC-CNN is more than 0.95 and the mean absolute error of prediction value from MFCC-CNN is less than 0.55, which fully meets the need of engineering. Finally, the newly proposed MFCC-CNN approach may be extended to address other vehicle noises in the future.

A data mining approach for prediction of quality attributes in Palmer mango from images

The monitoring of quality attributes such as, total soluble solids (TSS), mass, acidity and firmness are essential for a better postharvest conservation of mango.
 This work proposes a non destructive approach for prediction of those quality attributes using digital images. The proposed approach is composed by three stages: 1) specification of the sampling parameters of mango, 2) identification of digital images pre-processing techniques and 3) utilization of the Random Forest technique as estimator of the quality attributes. In order to validate the proposed approach, a study comparing its performance with models found in literature was carried out. The study used two metrics of performance evaluation: the correlation coefficient (R) and the root mean square error (RMSE). In order to compare the differences of performance between the proposed approach and approaches found in literature, a paired t-student’s hypothesis test was carried out. Results show that the proposed approach has a superior performance regarding the existing ones, with confidence level of 95%.

Off-the-shelf Convolutional Neural Network (CNN) features for Automatic Face Quality Prediction

Estimation of face image quality helps in correctly recognizing faces which in turn helps in many practical applications related to face. This paper presents a face quality prediction approach using Off-the-Shelf CNN features. Here we evaluated three image descriptors-binary patterns (LBP), Histogram of oriented gradients (HOG), Oriented Fast and Rotated Brief (ORB), and deep Convolution Neural Network (CNN) Networks pre-trained on ImageNet-VGG19, ResNet50, and VGG Small (4 layers) for feature extraction to detect face region image quality. Furthermore, to classify extracted features, we have evaluated three classifiers, that are different from each other in their own ways (SVM, DT and MLP) For experimental analysis, we created a face quality dataset by collecting images from web and publicly available face datasets and manually labeled images under seven categories-Good and six bad quality classes (e.g. Expression, Makeup, Pose, Occlusion, Illumination and Blur). The accuracy of face image classification using VGG19 along with MLP as a classifier was the highest (i.e.98.76%) followed by ResNet50 and MLP at 98.69% of accuracy. The lowest accuracy was obtained with LBP and SVM, this shows that deep features gives a better solution.

IRIS-GRAPE: An approach for prediction of quality attributes in vineyard grapes inspired by iris biometric recognition

The determination of the period of harvest is essential in the vineyard. For that, attributes of quality such as Total Soluble Solids (TSS) and phenolic compounds are constantly monitored along the maturation. This work proposes a new non-destructive approach for prediction of TSS, total anthocyanins and yellow flavonoids using RGB images, called IRIS-GRAPE. It is inspired by the process of biometric recognition using the iris. In order to validate the proposed approach, a study comparing its performance with the traditional method was performed, using the average of RGB pixel values of the region of interest (ROI) as input variables for a multiple linear regression. The study used two performance evaluation metrics: the correlation coefficient (rP) and the mean square error (MSE). In order to compare the performance differences between the proposed approach, IRIS-GRAPE, and the traditional approach, hypothesis tests were done. The results show that the proposed approach has a superior performance than the traditional method with a confidence level of 95%.

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.

Mamdani-Fuzzy Modeling Approach for Quality Prediction of Non-Linear Laser Lathing Process

Lathing is a process to fashioning stock materials into desired cylindrical shapes which usually performed by traditional lathe machine. But, the recent rapid advancements in engineering materials and precision demand gives a great challenge to the traditional method. The main drawback of conventional lathe is its mechanical contact which brings to the undesirable tool wear, heat affected zone, finishing, and dimensional accuracy especially taper quality in machining of stock with high length to diameter ratio. Therefore, a novel approach has been devised to investigate in transforming a 2D flatbed CO2 laser cutting machine into 3D laser lathing capability as an alternative solution. Three significant design parameters were selected for this experiment, namely cutting speed, spinning speed, and depth of cut. Total of 24 experiments were performed with eight (8) sequential runs where they were then replicated three (3) times. The experimental results were then used to establish Mamdani - Fuzzy predictive model where it yields the accuracy of more than 95%. Thus, the proposed Mamdani - Fuzzy modelling approach is found very much suitable and practical for quality prediction of non-linear laser lathing process for cylindrical stocks of 10mm diameter.

Multi-model quality prediction approach using fuzzy C-means clustering and support vector regression

Quality prediction of complex production process has increasingly attracted the interests of manufacturers and researchers. Complex production process has the characteristics of sub-process mutual ...

Data Mining Approach for Quality Prediction and Fault Diagnosis of Injection Molding Process

Objectives: To implement data mining approach to diagnose the causes of faults occurring in the injection molding product and to predict the quality of product for a particular setting of process parameters. Methods and Statistical Analysis: Decision Tree, k-Nearest Neighbor (k-NN) and Polynomial by Binomial classification techniques are used to build the data mining models by training them on dataset collected during the injection molding of a cap for 25 ml container. Findings: These models are evaluated on test dataset and their prediction accuracy is found to be 95%. Sink marks are caused by low injection speed, nozzle temperature and injection pressure. Low nozzle and mould temperatures and injection pressure resulted in short shot. High barrel temperature at Zone 2 and injection speed are responsible for burn marks in the product. Applications/Improvements: The higher prediction accuracy of these models is helpful in predicting the quality of product before its manufacture and thereby avoiding the production of defective parts. This approach can be further extended for injection molded parts made out of various plastic materials and process conditions.

Predicting Query Quality for Applications of Text Retrieval to Software Engineering Tasks

Context: Since the mid-2000s, numerous recommendation systems based on text retrieval (TR) have been proposed to support software engineering (SE) tasks such as concept location, traceability link recovery, code reuse, impact analysis, and so on. The success of TR-based solutions highly depends on the query submitted, which is either formulated by the developer or automatically extracted from software artifacts. Aim: We aim at predicting the quality of queries submitted to TR-based approaches in SE. This can lead to benefits for developers and for the quality of software systems alike. For example, knowing when a query is poorly formulated can save developers the time and frustration of analyzing irrelevant search results. Instead, they could focus on reformulating the query. Also, knowing if an artifact used as a query leads to irrelevant search results may uncover underlying problems in the query artifact itself. Method: We introduce an automatic query quality prediction approach for software artifact retrieval by adapting NL-inspired solutions to their use on software data. We present two applications and evaluations of the approach in the context of concept location and traceability link recovery, where TR has been applied most often in SE. For concept location, we use the approach to determine if the list of retrieved code elements is likely to contain code relevant to a particular change request or not, in which case, the queries are good candidates for reformulation. For traceability link recovery, the queries represent software artifacts. In this case, we use the query quality prediction approach to identify artifacts that are hard to trace to other artifacts and may therefore have a low intrinsic quality for TR-based traceability link recovery. Results: For concept location, the evaluation shows that our approach is able to correctly predict the quality of queries in 82% of the cases, on average, using very little training data. In the case of traceability recovery, the proposed approach is able to detect hard to trace artifacts in 74% of the cases, on average. Conclusions: The results of our evaluation on applications for concept location and traceability link recovery indicate that our approach can be used to predict the results of a TR-based approach by assessing the quality of the text query. This can lead to saved effort and time, as well as the identification of software artifacts that may be difficult to trace using TR.

Simulating receptive fields of human visual cortex for 3D image quality prediction.

Quality assessment of 3D images presents many challenges when attempting to gain better understanding of the human visual system. In this paper, we propose a new 3D image quality prediction approach by simulating receptive fields (RFs) of human visual cortex. To be more specific, we extract the RFs from a complete visual pathway, and calculate their similarity indices between the reference and distorted 3D images. The final quality score is obtained by determining their connections via support vector regression. Experimental results on three 3D image quality assessment databases demonstrate that in comparison with the most relevant existing methods, the devised algorithm achieves high consistency alignment with subjective assessment, especially for asymmetrically distorted stereoscopic images.

Sound quality prediction of vehicle interior noise using deep belief networks

The sound quality of vehicle interior noise strongly influences passengers’ psychological and physiological perceptions. To predict the sound quality of interior noise, a vehicle road test with four compact cars has been conducted. All recorded interior noise signals have been denoised via a discrete wavelet transform (DWT) denoising procedure and subsequently evaluated subjectively through the anchor semantic differential (ASD) test by a jury. In addition, a novel prediction method, namely, regression-based deep belief networks (DBNs), which substitute the support vector regression (SVR) layer for the linear softmax classification layer at the top of the general DBN’s structure, has been proposed to predict the interior sound quality. The parameter selection of the DBN model has been compared and studied using a grid search. In addition, four conventional machine-learning-based methods have been introduced to enable a comparison of the performance with the newly developed DBNs. Furthermore, the feature fusion ability of DBNs has been studied by varying the amount of information that the dataset offers. The results show the following: (1) The accuracy and robustness of the proposed DBN-based sound quality prediction approach are better than those of the 4 other referenced methods. (2) The multiple-feature fusing process can strongly affect the prediction performance. (3) Finally, the unsupervised pre-training process of the DBNs can enhance the information fusing ability. Finally, the newly proposed regression-based DBN approach may be extended to address other vehicle noises in the future.

Optimization of Astaxanthin microencapsulation in hydrophilic carriers using response surface methodology.

Astaxanthin (3, 3'-dihydroxy-β, β-carotene-4, 4'-dione; AST) belongs to class of xanthophylls and is very effective antioxidant. It has very poor aqueous solubility resulting in lower bioavailability which presents major concerns in product development for oral use. AST was microencapsulated with soluble polymers using spray drying to improve its solubility and bioavailability. Quality by Design (QbD), a widely used approach for prediction of quality for desired specifications and effects was applied Design of Experiments (DOE), a useful component of QbD was utilized to understand the effect of variables and their interactions. Different formulation variables like ratio of hydrophilic carriers, concentration of solubilizers and homogenizer speed were challenged in the experimental design during the process of microencapsulation. The optimized formulation showed consistent release rate and characterization was done by DSC, XRD and SEM study. Percent cell growth inhibition was increased in optimized formulation as compared to plain AST. This QbD study can form a basis for further development of poorly water soluble AST formulation by oral route with improved bioavailability on larger scale.

Final quality prediction for multi-phase batch process based on phase cumulative product quality model

A novel online final product quality prediction scheme is proposed in this paper for the improvement of quality prediction in multi-phase batch processes. Phase cumulative product quality (PCPQ), which is quality cumulated from the beginning of the phase to the end, is introduced for quality prediction, and final product quality prediction offline is achieved by cumulating all the predicted PCPQ based on the corresponding PCPQ model. In this way, the quality prediction approach proposed not only explores the different effects of process variables in different phases on final product quality, but also takes the common effects of process variables in different phases into account. The PCPQ model and remained phase cumulative product quality (RPCPQ) model are combined to improve online prediction precision, without the missing observations estimation. The proposed approach is applied to a simulated penicillin fermentation process and the results of simulation demonstrate effectiveness and superiority.

A SNCCDBAGG-Based NN Ensemble Approach for Quality Prediction in Injection Molding Process

This paper presents a SNCCDBAGG-based neural network (NN) ensemble approach for quality prediction in injection molding process. Bagging is used to create NNs for the ensemble by independently training these NNs on different training sets. Negative correlation learning via correlation-corrected data (NCCD) is used to achieve negative correlation of each network's error against errors for the rest of the ensemble by training transformed target data for NN in the ensemble as the desired network output for some epochs. A selection-based strategy is proposed to improve generalization ability when combining Bagging and NCCD. Experimental results show its good performance on quality predicting in injection molding process compared with single NN predictor and NCCD predictor.