Quality Estimation Model Research Articles

Robust Self-Constructing Fuzzy Neural Network-Based Online Estimation for Industrial Product Quality

Online estimation for product quality is crucial for improving industrial process efficiency. However, model degradation and outliers usually challenge industrial quality estimation models. To tackle the above problems, a robust self-constructing fuzzy neural network (RSC-FNN) is developed in the article. In the RSC-FNN, the rules can be automatically created or pruned, obtaining the online self-constructing mechanism (OSCM). First, an online error compensation algorithm is developed to generate new rules. Second, the model performance and contribution of existing rules are evaluated online to delete redundant rules. Thus, the OSCM effectively improves the structural adaptability and compactness of the RSC-FNN. Moreover, the correntropy-induced criterion, which can handle complex outliers, is modified for the parameter learning algorithm. Hence, the adverse effect of outliers can be suppressed during the parameter updating process. Besides, we analyze the convergence of the RSC-FNN to ensure its feasibility in industrial applications. Finally, two industrial applications are studied to test the effectiveness of the RSC-FNN. Compared with other FNN <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">s</sub> , the results indicate that the RSC-FNN performs better in learning efficiency, structure compactness, and robustness.

Face Recognition Bias Assessment through Quality Estimation Models

Recent advances in facial recognition technology have achieved outstanding performance, but unconstrained face recognition remains an ongoing issue. Facial-image-quality-evaluation algorithms evaluate the quality of the input samples, providing crucial information about the accuracy of recognition decisions. By doing so, this can lead to improved results in challenging scenarios. In recent years, significant progress has been made in assessing the quality of facial images. The computation of quality scores has become highly precise and closely correlated with the model results. In this paper, we reviewed and analyzed the existing biases of cutting-edge quality-estimation techniques for face recognition. Our experimentation focused on the quality estimators developed by MagFace, FaceQNet, and SER-FIQ and were evaluated on the CelebA reference dataset. A study of bias in the face-recognition model was conducted by analyzing the quality scores presented in each article. This allowed for an examination of existing biases within both the quality estimators and the face-recognition models.

How well do collaboration quality estimation models generalize across authentic school contexts?

AbstractMultimodal learning analytics (MMLA) research has made significant progress in modelling collaboration quality for the purpose of understanding collaboration behaviour and building automated collaboration estimation models. Deploying these automated models in authentic classroom scenarios, however, remains a challenge. This paper presents findings from an evaluation of collaboration quality estimation models. We collected audio, video and log data from two different Estonian schools. These data were used in different combinations to build collaboration estimation models and then assessed across different subjects, different types of activities (collaborative‐writing, group‐discussion) and different schools. Our results suggest that the automated collaboration model can generalize to the context of different schools but with a 25% degradation in balanced accuracy (from 82% to 57%). Moreover, the results also indicate that multimodality brings more performance improvement in the case of group‐discussion‐based activities than collaborative‐writing‐based activities. Further, our results suggest that the video data could be an alternative for understanding collaboration in authentic settings where higher‐quality audio data cannot be collected due to contextual factors. The findings have implications for building automated collaboration estimation systems to assist teachers with monitoring their collaborative classrooms. Practitioners notesWhat is already known about this topic Multimodal learning analytics researchers have established several features as potential indicators for collaboration quality, e.g., speaking time or joint visual attention. The current state of the art has shown the feasibility of building automated collaboration quality models. Recent research has provided preliminary evidence of the generalizability of developed automated models across contexts different in terms of given task and subject. What does this paper add This paper offers collaboration indicators for different types of collaborative learning activities in authentic classroom settings. The paper includes a systematic investigation into collaboration quality automated model's generalizability across different tasks, types of tasks and schools. This paper also offers a comparison between different modalities' potential to estimate collaboration quality in authentic settings. Implications for practice The findings inform the development of automated collaboration monitoring systems for authentic classroom settings. This paper provides evidence on across‐school generalizability capabilities of collaboration quality estimation models.

Measurement of Turbidity and Total Suspended Matter in the Albufera of Valencia Lagoon (Spain) Using Sentinel-2 Images

In the context of freshwater ecosystems, turbidity and suspended solids play crucial roles, with their levels significantly influenced by anthropogenic activities. This study focuses on assessing and monitoring these parameters in Albufera de Valencia using Sentinel-2 imagery. The primary aim is to establish reliable estimation algorithms that can contribute to effective ecosystem management. This study calibrated and validated algorithms for estimating turbidity and suspended solids. The R783 × R705/R490 model proved to have the best performance for estimating turbidity and total solids in Albufera. However, R783/R490 obtained a higher coefficient of determination for the organic part, while the R705 band was selected for the inorganic part. However, to achieve better estimates of turbidity and inorganic matter, more research is needed in the future. The implications of excessive suspended solids are underscored, including the depletion of dissolved oxygen and reduced primary productivity due to limited light penetration and habitat availability. Collaboration between disciplines such as limnology, optics, and water chemistry is crucial to advance water quality estimation models in lakes and lagoons such as Albufera. By integrating expertise and approaches from these diverse fields, new knowledge can be gained, and the basis for more effective management and conservation strategies can be laid.

Deep Learning-Based Link Quality Estimation for RIS-Assisted UAV-Enabled Wireless Communications System.

In recent years, unmanned aerial vehicles (UAVs) have become a valuable platform for many applications, including communication networks. UAV-enabled wireless communication faces challenges in complex urban and dynamic environments. UAVs can suffer from power limitations and path losses caused by non-line-of-sight connections, which may hamper communication performance. To address these issues, reconfigurable intelligent surfaces (RIS) have been proposed as helpful technologies to enhance UAV communication networks. However, due to the high mobility of UAVs, complex channel environments, and dynamic RIS configurations, it is challenging to estimate the link quality of ground users. In this paper, we propose a link quality estimation model using a gated recurrent unit (GRU) to assess the link quality of ground users for a multi-user RIS-assisted UAV-enabled wireless communication system. Our proposed framework uses a time series of user channel data and RIS phase shift information to estimate the quality of the link for each ground user. The simulation results showed that the proposed GRU model can effectively and accurately estimate the link quality of ground users in the RIS-assisted UAV-enabled wireless communication network.

Multi-view fusion for universal translation quality estimation

Machine translation quality estimation (QE) aims to evaluate the result of translation without reference. Despite the progress it has made, state-of-the-art QE models are proven to be biased. More specifically, they over-rely on spurious statistical features while ignoring the bilingual semantic adequacy, leading to performance degradation. Besides, existing approaches require large amounts of annotation data, restricting their applications in new domains and languages. In this work, we propose a universal framework for quality estimation based on multi-view fusion. We first introduce noise to the target side of the parallel sentence pair, either by pre-trained language model or by large language model. After that, with the clean parallel pairs and the noised pairs as different views, the QE model is trained to distinguish the clean pairs from the noised ones. Our method can improve the accuracy and generalizability in supervised scenario, and can solely perform estimation in zero-shot scenario. We perform experiments on WMT QE evaluation datasets under different scenarios, verifying the effectiveness of our method. We also make an in-depth investigation of the bias of QE model.

Sugarcane polyphenol oxidase: Structural elucidation using molecular modeling and docking analyses

Polyphenol oxidase (PPO) enzymes induce undesirable browning in fruits, vegetables, and juices like sugarcane and apple. Inactivation of PPO is crucial to mitigate this issue, achieved through methods like heat, radiation, ultrasound, pH adjustment, adsorbent addition, and inhibitors. Inhibitor selection is traditionally a time-consuming trial-and-error process. This study aimed to develop a homology model of sugarcane PPO and to streamline inhibitor selection using a rational approach, relying on knowledge of PPO's structure and active site. The research utilized homology modeling through SWISS-MODELER to predict the 3D structures of two types of sugarcane copper-based PPOs: met-PPO (Cu-Cu active site) and oxy-PPO (Cu-O-Cu active site), both composed of 235 amino acids. Model quality was assessed using Global Model Quality Estimation (GMQE) and Qualitative Model Energy Analysis (QMEAN), yielding favorable scores of 0.17 (GMQE), 0.44 ± 0.05 (QMEAN Co-Global) and z-score of –4.03. Ramachandran analysis indicated 78.8 % and 17.5 % of amino acid residues fell within the most favored and additional allowed regions, respectively. Docking analysis revealed strong affinities between m-hydroxybenzoic acid and p-hydroxybenzoic acid with binding energies of –4.40 Kcal/mol and –4.38 Kcal/mol, respectively, for met-PPO and oxy-PPO. Identified active site residues are ARG369, HIS325, GLU321, ALA361, and TRP313. This study enhances comprehension of sugarcane PPO and its active site, aiding rational inhibitor design to counteract undesired browning reactions.

Denoising Pre-training for Machine Translation Quality Estimation with Curriculum Learning

Quality estimation (QE) aims to assess the quality of machine translations when reference translations are unavailable. QE plays a crucial role in many real-world applications of machine translation. Because labeled QE data are usually limited in scale, recent research, such as DirectQE, pre-trains QE models with pseudo QE data and obtains remarkable performance. However, there tends to be inevitable noise in the pseudo data, hindering models from learning QE accurately. Our study shows that the noise mainly comes from the differences between pseudo and real translation outputs. To handle this problem, we propose CLQE, a denoising pre-training framework for QE based on curriculum learning. More specifically, we propose to measure the degree of noise in the pseudo QE data with some metrics based on statistical or distributional features. With the guidance of these metrics, CLQE gradually pre-trains the QE model using data from cleaner to noisier. Experiments on various benchmarks reveal that CLQE outperforms DirectQE and other strong baselines. We also show that with our framework, pre-training converges faster than directly using the pseudo data. We make our CLQE code available (https://github.com/NJUNLP/njuqe).

Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection

AbstractNeural sequence generation models are known to “hallucinate”, by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. In this work, we first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinated vs. non-hallucinated outputs generated via source perturbations. We then show that these symptoms are reliable indicators of natural hallucinations, by using them to design a lightweight hallucination detector which outperforms both model-free baselines and strong classifiers based on quality estimation or large pre-trained models on manually annotated English-Chinese and German-English translation test beds.

EfficientNetV2 Based Ensemble Model for Quality Estimation of Diabetic Retinopathy Images from DeepDRiD

Diabetic retinopathy (DR) is one of the major complications caused by diabetes and is usually identified from retinal fundus images. Screening of DR from digital fundus images could be time-consuming and error-prone for ophthalmologists. For efficient DR screening, good quality of the fundus image is essential and thereby reduces diagnostic errors. Hence, in this work, an automated method for quality estimation (QE) of digital fundus images using an ensemble of recent state-of-the-art EfficientNetV2 deep neural network models is proposed. The ensemble method was cross-validated and tested on one of the largest openly available datasets, the Deep Diabetic Retinopathy Image Dataset (DeepDRiD). We obtained a test accuracy of 75% for the QE, outperforming the existing methods on the DeepDRiD. Hence, the proposed ensemble method may be a potential tool for automated QE of fundus images and could be handy to ophthalmologists.

Machine-learning based automatic assessment of communication in interpreting

Communication assessment in interpreting has developed into an area with new models and continues to receive growing attention in recent years. The process refers to the assessment of messages composed of both “verbal” and “nonverbal” signals. A few relevant studies revolving around automatic scoring investigated the assessment of fluency based on objective temporal measures, and the correlation between the machine translation metrics and human scores. There is no research exploring machine-learning-based automatic scoring in-depth integrating parameters of delivery and information. What remains fundamentally challenging to demonstrate is which parameters, extracted through an automatic methodology, predict more reliable results. This study presents an original study with the aim to propose and test a machine learning approach to automatically assess communication in English/Chinese interpreting. It proposes to build predictive models using machine learning algorithms, extracting parameters for delivery, and applying a translation quality estimation model for information assessment to describe the final model. It employs the K-nearest neighbour algorithm and support vector machine for further analysis. It is found that the best machine-learning model built with all features by Support Vector Machine shows an accuracy of 62.96%, which is better than the K-nearest neighbour model with an accuracy of 55.56%. The assessment results of the pass level can be accurately predicted, which indicates that the machine learning models are able to screen the interpretations that pass the exam. The study is the first to build supervised machine learning models integrating both delivery and fidelity features to predict quality of interpreting. The machine learning models point to the great potential of automatic scoring with little human evaluation involved in the process. Automatic assessment of communication is expected to complete multi-tasks within a brief period by taking both holistic and analytical approaches to assess accuracy, fidelity and delivery. The proposed automatic scoring system might facilitate human-machine collaboration in the future. It can generate instant feedback for students by evaluating input renditions or abridge the workload for educators in interpreting education by screening performance for subsequent human scoring.

Retrieving Eutrophic Water in Highly Urbanized Area Coupling UAV Multispectral Data and Machine Learning Algorithms

With the rapid development of urbanization and a population surge, the drawback of water pollution, especially eutrophication, poses a severe threat to ecosystem as well as human well-being. Timely monitoring the variations of water quality is a precedent to preventing the occurrence of eutrophication. Traditional monitoring methods (station monitoring or satellite remote sensing), however, fail to real-time obtain water quality in an accurate and economical way. In this study, an unmanned aerial vehicle (UAV) with a multispectral camera is used to acquire the refined remote sensing data of water bodies. Meanwhile, in situ measurement and sampling in-lab testing are carried out to obtain the observed values of four water quality parameters; subsequently, the comprehensive trophic level index (TLI) is calculated. Then three machine learning algorithms (i.e., Extreme Gradient Boosting (XGB), Random Forest (RF) and Artificial Neural Network (ANN)) are applied to construct the inversion model for water quality estimation. The measured values of water quality showed that the trophic status of the study area was mesotrophic or light eutrophic, which was consistent with the government’s water-control ambition. Among the four water quality parameters, TN had the highest correlation (r = 0.81, p = 0.001) with TLI, indicating that the variation in TLI was inextricably linked to TN. The performances of the three models were satisfactory, among which XGB was considered the optimal model with the best accuracy validation metrics (R2 = 0.83, RMSE = 0.52). The spatial distribution map of water quality drawn by the XGB model was in good agreement with the actual situation, manifesting the spatial applicability of the XGB model inversion. The research helps guide effective monitoring and the development of timely warning for eutrophication.

Neural Quality Estimation Based on Multiple Hypotheses Interaction and Self-Attention for Grammatical Error Correction

The English grammatical error correction system is suitable for the English learning environment, with the goal of accurately correcting errors in learners’ writing. However, false corrections are often generated in practical applications, and many errors cannot be corrected, thus misleading learners. The quality estimation model is beneficial to ensure that learners obtain accurate grammatical error correction results and avoid misleading sentences caused by error corrections. Grammatical error correction models can generate multiple hypotheses of higher quality, but existing quality estimation models do not consider interactions between different hypotheses. Based on this, we propose a model based on multiple hypotheses interaction and self-attention, BGANet, for English grammatical error correction quality estimation. BGANet builds interactions between multiple hypotheses, extracts and aggregates grammatical error correction evidence in hypotheses through two kinds of self-attention mechanisms, and evaluates the quality of the generated hypotheses. Experiments on four grammatical error correction datasets show that BGANet has better quality estimation performance.

Efficient Route Planning Using Temporal Reliance of Link Quality for Highway IoV Traffic Environment

Intermittently connected vehicular networks, terrain of the highway, and high mobility of the vehicles are the main critical constraints of highway IoV (Internet of Vehicles) traffic environment. These cause GPS outage problem and the existence of short-lived wireless mobile links that reduce the performance of designed routing approaches. Nevertheless, geographic routing has attracted a lot of attention from researchers as a potential means of accurate and efficient information delivery. Various distance-based routing protocols have been proposed in the literature, with an emphasis on restricting the forwarding area to the next forwarding vehicle. Many of these protocols have issues with significant one-hop link disconnection, long end-to-end delays, and low throughput even at normal vehicle speeds in high-vehicular-density environments due to frequently interrupted wireless links. In this paper, an efficient geocast routing (EGR) approach for highway IoV–traffic environment considering the shadowing fading condition is proposed. In EGR, a geometrical localization for GPS outage problem and a temporal link quality estimation model considering underlying vehicular movement have been proposed. Geocast routing to select a next forwarding vehicle from forward region by utilizing temporal link quality is proposed for four different scenarios. To evaluate the effectiveness and scalability of EGR, a comparative performance evaluation based on simulations has been performed. It is clear from the analysis of the results that EGR performs better than state-of-the-art approaches in highway traffic environment in terms of handling the problem of wireless communication link breakage and throughput, as well as ensuring the faster delivery of the messages.

CLASSIFICATION REVIEW OF RAW SUBJECTIVE SCORES TOWARDS STATISTICAL ANALYSIS

We proposed a no reference model for quality estimation based on compression artifacts which are principal factor for determining the QoE compared to varying depth range within compression. Moreover, in our past research work, contents with strong compression have been rejected by the Subjects who graded quality of distorted videos and judged unacceptable. The results of our proposed approach conrm that our subjective scores of 120 videos are related to control of visible spatial artifacts of reconstructed videos not distorted and with consideration of User Experience (UX), It was traced out by rening raw subjective scores, it happened due to coding of spatial and temporal perceptual information according to H.264 standards mentioned by ITU only for video quality assessment, i.e., instead of coding spatial of chrominance and temporal information of luminance plane, selected test sequences were coded within luminance plane for both spatial and temporal information

Long-Term Monitoring of an Urban Stormwater Infiltration Trench in South Korea with Assessment Using the Analytic Hierarchy Process

Evaluating the functionality of small and decentralized low-impact development (LID) technologies often requires extensive labor, time, and costs for water quality analysis. In order to reduce these in an infiltration trench in South Korea, monitoring data gathered over a period of 8 years were used to determine its long-term performance, establish a stormwater quality estimation model, and develop a comprehensive evaluation tool. Our findings show that the infiltration trench can treat up to 90% of the stormwater runoff from a paved road but would require annual maintenance to minimize the reduction in infiltration capacity. The facility was able to remove an average of 83% of total suspended solids (TSS), 75% of biochemical oxygen demand (BOD), 80% of chemical oxygen demand (COD), 76% of total nitrogen (TN), and 79% of total phosphorus (TP), with the highest removal efficiencies observed after maintenance was conducted. Rainfall depth and air quality parameters (i.e., PM2.5 and PM10) were found to be positively correlated with TSS, COD, TN, and TP. These parameters were then used to develop a model for the estimation of influent stormwater quality, which can help in estimating the effluent water quality based on the average removal efficiencies. Furthermore, a comprehensive evaluation tool considering indicators such as treatment efficiency, cultural benefits, and facility and operating conditions was established through the analytic hierarchy process (AHP). Aside from determining the facility’s overall efficiency, this can also serve as a diagnostic tool to identify whether maintenance is needed or not. While atmospheric and hydrological characteristics differ in different regions, and the results may vary if applied in other facilities, this study can serve as a guide to the effective and efficient evaluation of similar stormwater management facilities in South Korea.

Deep-Reinforcement-Learning-Based Drone Base Station Deployment for Wireless Communication Services

Over the last few years, drone base station (DBS) technology has been recognized as a promising solution to the problem of network design for wireless communication systems, due to its highly flexible deployment and dynamic mobility features. This article focuses on the 3-D mobility control of the DBS to boost transmission coverage and network connectivity. We propose a dynamic and scalable control strategy for drone mobility using deep reinforcement learning (DRL). The design goal is to maximize communication coverage and network connectivity for multiple real-time users over a time horizon. The proposed method functions according to the received signals of mobile users, without the information of user locations. It is divided into two hierarchical stages. First, a time-series convolutional neural network (CNN)-based link quality estimation model is used to determine the link quality at each timeslot. Second, a deep <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning algorithm is applied to control the movement of the DBS in hotspot areas to meet user requirements. Simulation results show that the proposed method achieves significant network performance in terms of both communication coverage and network throughput in a dynamic environment, compared with the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning algorithm.

An ensemble machine learning model for water quality estimation in coastal area based on remote sensing imagery

The accurate estimation of coastal water quality parameters (WQPs) is crucial for decision-makers to manage water resources. Although various machine learning (ML) models have been developed for coastal water quality estimation using remote sensing data, the performance of these models has significant uncertainties when applied to regional scales. To address this issue, an ensemble ML-based model was developed in this study. The ensemble ML model was applied to estimate chlorophyll-a (Chla), turbidity, and dissolved oxygen (DO) based on Sentinel-2 satellite images in Shenzhen Bay, China. The optimal input features for each WQP were selected from eight spectral bands and seven spectral indices. A local explanation strategy termed Shapley Additive Explanations (SHAP) was employed to quantify contributions of each feature to model outputs. In addition, the impacts of three climate factors on the variation of each WQP were analyzed. The results suggested that the ensemble ML models have satisfied performance for Chla (errors = 1.7%), turbidity (errors = 1.5%) and DO estimation (errors = 0.02%). Band 3 (B3) has the highest positive contribution to Chla estimation, while Band Ration Index2 (BR2) has the highest negative contribution to turbidity estimation, and Band 7 (B7) has the highest positive contribution to DO estimation. The spatial patterns of the three WQPs revealed that the water quality deterioration in Shenzhen Bay was mainly influenced by input of terrestrial pollutants from the estuary. Correlation analysis demonstrated that air temperature (Temp) and average air pressure (AAP) exhibited the closest relationship with Chla. DO showed the strongest negative correlation with Temp, while turbidity was not sensitive to Temp, average wind speed (AWS), and AAP. Overall, the ensemble ML model proposed in this study provides an accurate and practical method for long-term Chla, turbidity, and DO estimation in coastal waters.

A Software Quality Prediction Model for Aspect Oriented System using Neuro-Fuzzy Approach

Nowadays, the usage of software has increased exponentially in various fields like education systems, industries, health systems, and many others. Various software architectures are already available in the market e.g. modular oriented, component-based, object-oriented, aspect-oriented, etc. Aspect-Oriented (AO) system software has gained much attention due to its superior features to the aforementioned systems. However, AO systems face the challenges of being complex and hard testing environment, a quality assessment of these systems is necessary. In this paper, a software quality estimation model for aspect oriented system using neuro-fuzzy approach has been developed. For which, a detailed study on aspect oriented systems has been accomplished in terms of various attributes affecting the quality of these software. In this paper, a framework of software quality prediction model has been designed using the adaptive neuro-fuzzy inference engine (ANFIS) approach. Data of 200 software pieces have been collected in this study where 150 software data is used to train the ANFIS model whereas 50 software data is used for testing purposes. The quality estimated by the proposed ANFIS model is compared with the actual quality of these software data and quantitative analysis is performed in terms of error measures. Finally, it was found that the proposed ANFIS model worked better in terms of MSE, MRE, MARE, MBRE, and MIBRE error measures.

Urban Air Quality Assessment by Fusing Spatial and Temporal Data from Multiple Study Sources Using Refined Estimation Methods

In urban environmental management and public health evaluation efforts, there is an urgent need for fine-grained urban air quality monitoring. However, the high price and sparse distribution of air quality monitoring equipment make it difficult to develop effective and comprehensive fine-scale monitoring at the city scale. This has also led to air quality estimation methods based on incomplete monitoring data, which lack the ability to detect urban air quality differences within a neighborhood. To address this problem, this study proposes a refined urban air quality estimation method that fuses multisource spatio-temporal data. Based on the fact that urban air quality is easily affected by social activities, this method integrates meteorological data with urban social activity data to form a comprehensive environmental data set. It uses the spatio-temporal feature extraction model to extract the multi-source spatio-temporal features of the comprehensive environmental data set. Finally, the improved cascade forest algorithm is used to fit the relationship between the multisource spatio-temporal features and the air quality index (AQI) to construct an air quality estimation model, and the model is used to estimate the hourly PM2.5 index in Beijing on a 1 km × 1 km grid. The results show that the estimation model has excellent performance, and its goodness-of-fit (R2) and root mean square error (RMSE) reach 0.961 and 17.47, respectively. This method effectively achieves the assessment of urban air quality differences within a neighborhood and provides a new strategy for preventing information fragmentation and improving the effectiveness of information representation in the data fusion process.