Quality Assessment Model Research Articles

Review of Translation Quality Assessment Research: Current Studies and Development

The development of computer automatic assessment and corpus linguistics has provided a new research idea for translation quality assessment. This paper reviews the current situation of translation quality assessment at home and abroad and its application in translation teaching. Findings are that most of the current translation quality assessments are static, and the empirical research applied in translation teaching is not sufficient. Therefore, how to make the assessment model of translation quality keep pace with translation teachers and learners’ needs is an unavoidable issue that cannot be ignored in the future translation quality assessment research.

Xception-based architecture with cross-sampled training for Image Quality Assessment on KonIQ-10k

Image quality assessment is a~crucial task in various fields such as digital photography, online content creation, and automated quality control, as it ensures an optimal visual experience and aids in maintaining consistent standards. In this paper, we propose an efficient method for training image quality assessment models on the KonIQ-10k dataset. Our novel approach utilizes a~dual-Xception architecture that analyzes both the image content and additional image parameters, outperforming traditional single convolutional models. We introduce cross-sampling methods with random draw sampling of instances from majority classes, effectively enhancing prediction quality in the Mean Opinion Score (MOS) ranges that are underrepresented in the database. This methodology allows us to achieve near state-of-the-art results with limited computing costs and resources. Most importantly, our predictions across the entire spectrum of MOS values maintain consistent quality. Because of using a~novel and highly effective method for image sampling, we achieved these results with much lower computational cost, making our approach the most effective way of MOS estimation on the KonIQ-10k database.

A conceptual model for ontology quality assessment

With the continuous advancement of methods, tools, and techniques in ontology development, ontologies have emerged in various fields such as machine learning, robotics, biomedical informatics, agricultural informatics, crowdsourcing, database management, and the Internet of Things. Nevertheless, the nonexistence of a universally agreed methodology for specifying and evaluating the quality of an ontology hinders the success of ontology-based systems in such fields as the quality of each component is required for the overall quality of a system and in turn impacts the usability in use. Moreover, a number of anomalies in definitions of ontology quality concepts are visible, and in addition to that, the ontology quality assessment is limited only to a certain set of characteristics in practice even though some other significant characteristics have to be considered for the specified use-case. Thus, in this research, a comprehensive analysis was performed to uncover the existing contributions specifically on ontology quality models, characteristics, and the associated measures of these characteristics. Consequently, the characteristics identified through this review were classified with the associated aspects of the ontology evaluation space. Furthermore, the formalized definitions for each quality characteristic are provided through this study from the ontological perspective based on the accepted theories and standards. Additionally, a thorough analysis of the extent to which the existing works have covered the quality evaluation aspects is presented and the areas further to be investigated are outlined.

2BiVQA: Double Bi-LSTM-based Video Quality Assessment of UGC Videos

Recently, with the growing popularity of mobile devices as well as video sharing platforms (e.g., YouTube, Facebook, TikTok, and Twitch), User-Generated Content (UGC) videos have become increasingly common and now account for a large portion of multimedia traffic on the internet. Unlike professionally generated videos produced by filmmakers and videographers, typically, UGC videos contain multiple authentic distortions, generally introduced during capture and processing by naive users. Quality prediction of UGC videos is of paramount importance to optimize and monitor their processing in hosting platforms, such as their coding, transcoding, and streaming. However, blind quality prediction of UGC is quite challenging, because the degradations of UGC videos are unknown and very diverse, in addition to the unavailability of pristine reference. Therefore, in this article, we propose an accurate and efficient Blind Video Quality Assessment (BVQA) model for UGC videos, which we name 2BiVQA for double Bi-LSTM Video Quality Assessment. 2BiVQA metric consists of three main blocks, including a pre-trained Convolutional Neural Network to extract discriminative features from image patches, which are then fed into two Recurrent Neural Networks for spatial and temporal pooling. Specifically, we use two Bi-directional Long Short-term Memory networks, the first is used to capture short-range dependencies between image patches, while the second allows capturing long-range dependencies between frames to account for the temporal memory effect. Experimental results on recent large-scale UGC VQA datasets show that 2BiVQA achieves high performance at lower computational cost than most state-of-the-art VQA models. The source code of our 2BiVQA metric is made publicly available at https://github.com/atelili/2BiVQA .

Assessment of the Performances of the Protein Modeling Techniques Participating in CASP15 Using a Structure-Based Functional Site Prediction Approach: ResiRole.

Model quality assessments via computational methods which entail comparisons of the modeled structures to the experimentally determined structures are essential in the field of protein structure prediction. The assessments provide means to benchmark the accuracies of the modeling techniques and to aid with their development. We previously described the ResiRole method to gauge model quality principally based on the preservation of the structural characteristics described in SeqFEATURE functional site prediction models. We apply ResiRole to benchmark modeling group performances in the Critical Assessment of Structure Prediction experiment, round 15. To gauge model quality, a normalized Predicted Functional site Similarity Score (PFSS) was calculated as the average of one minus the absolute values of the differences of the functional site prediction probabilities, as found for the experimental structures versus those found at the corresponding sites in the structure models. The average PFSS per modeling group (gPFSS) correlates with standard quality metrics, and can effectively be used to rank the accuracies of the groups. For the free modeling (FM) category, correlation coefficients of the Local Distance Difference Test (LDDT) and Global Distance Test-Total Score (GDT-TS) metrics with gPFSS were 0.98239 and 0.87691, respectively. An example finding for a specific group is that the gPFSS for EMBER3D was higher than expected based on the predictive relationship between gPFSS and LDDT. We infer the result is due to the use of constraints imprinted by function that are a part of the EMBER3D methodology. Also, we find functional site predictions that may guide further functional characterizations of the respective proteins. The gPFSS metric provides an effective means to assess and rank the performances of the structure prediction techniques according to their abilities to accurately recount the structural features at predicted functional sites.

Mediating Role of Training Engagement Between Service Quality, Interface Quality, and Employee Creativity in Workforce of Ministry of Interior Abu Dhabi, UAE

Purpose: Employee creativity is vital for the success of any organization. Organizations conduct trainings and engagement of employees in the trainings helps organizations to get successful results. Theoretical framework: Employee creativity is highly dependent on service quality and interface quality. Therefore, this study is tailored to identify the mediating role of training engagement between service quality, interface quality and employee creativity. In order to test the framework developed on the basis of new website quality assessment model by the supporting role of engagement theory and investment theory of creativity. Design/methodology/approach: For testing the model, adopted questionnaires have been used and structural equation modeling has been applied. The findings revealed that training engagement significantly mediate the relationship between service quality, interface quality and employee creativity. Findings: The findings are significant for the policy makers to stress on engagement of employees in the training activities and by improving the service quality and interface quality to develop creativity among employees to get fruitful results. Research, Practical & Social implications: provides basics for understanding effectiveness e-learning, training engagement over employee creativity. As a result, it is revealed that training engagement in the presence of information qualities, system qualities, service qualities, interface qualities, and emotional qualities have a significant effect on employee creativity. Originality/value: the current research focuses on the importance of service quality and interface quality over training engagement and its interaction together over employee creativity.

Application of Decision Tree Classification Algorithm in Quality Assessment of Distance Learning in Colleges

INTRODUCTION: The quality assessment technology of distance education in colleges and universities, as the critical technology for identifying the quality of distance education in colleges and universities, is conducive to the improvement of the quality of distance teaching and the progress of the existing means and methods of distance education, which makes the means of distance teaching in colleges and universities rich in science.
 OBJECTIVES: Aiming at the evaluation methods of higher education institutions, there are problems such as insufficient objectivity and comprehensiveness of the evaluation system, single process, and inadequate quantitative analysis.
 METHODS:Proposes a decision tree and intelligent optimization algorithm for the college distance teaching quality assessment method. Firstly, the kernel principal component analysis method is used to carry out dimensionality reduction analysis on the index system of college distance teaching quality assessment; then, the decision tree parameters are optimized through the marine predator algorithm to construct a college distance teaching quality assessment model; finally, the robustness and efficiency of the proposed method are verified through simulation experimental analysis.
 RESULTS: The results show that the proposed method improves the accuracy of the assessment model.
 CONCLUSION: The problem of insufficient objective and scientific evaluation and low precision of distance teaching quality assessment methods in colleges and universities is solved.

Assessing protein model quality based on deep graph coupled networks using protein language model.

Model quality evaluation is a crucial part of protein structural biology. How to distinguish high-quality models from low-quality models, and to assess which high-quality models have relatively incorrect regions for improvement, are remain a challenge. More importantly, the quality assessment of multimer models is a hot topic for structure prediction. In this study, we propose GraphCPLMQA, a novel approach for evaluating residue-level model quality that combines graph coupled networks and embeddings from protein language models. The GraphCPLMQA consists of a graph encoding module and a transform-based convolutional decoding module. In encoding module, the underlying relational representations of sequence and high-dimensional geometry structure are extracted by protein language models with Evolutionary Scale Modeling. In decoding module, the mapping connection between structure and quality is inferred by the representations and low-dimensional features. Specifically, the triangular location and residue level contact order features are designed to enhance the association between the local structure and the overall topology. Experimental results demonstrate that GraphCPLMQA using single-sequence embedding achieves the best performance compared with the CASP15 residue-level interface evaluation methods among 9108 models in the local residue interface test set of CASP15 multimers. In CAMEO blind test (20 May 2022 to 13 August 2022), GraphCPLMQA ranked first compared with other servers (https://www.cameo3d.org/quality-estimation). GraphCPLMQA also outperforms state-of-the-art methods on 19,035 models in CASP13 and CASP14 monomer test set.

Assessment of the cultivated land quality in the black soil region of Northeast China based on the field scale.

In some developing countries, particularly China, a significant number of individual farmers manage small field scale of cultivated land. However, the existing research on cultivated land quality assessment mainly focuses on large-scale regions, establishing comprehensive index systems from a macro perspective, while lacking evaluations customized to individual farmers, who constitute a crucial component in agricultural production, and a demand-driven field-scale assessment of cultivated land quality. Therefore, we developed a field-scale index system that meets the needs of individual farmers in the black soil region of Northeast China. Additionally, we proposed a machine learning model for field-scale cultivated land quality assessment. The experimental results showed that our model achieved an [Formula: see text] value of 0.9660 and an [Formula: see text] of [Formula: see text] under fourfold cross-validation, which represents an improvement of 5.19% and a reduction of 1.13%, respectively, relative to the XGBoost model. Ultimately, we conducted obstacle factor diagnosis, aiming to assist individual farmers in identifying the existing issues in their cultivated land fields. This study not only provides guidance to individual farmers but also addresses the research gap in cultivated land quality assessment by offering an individual farmer demand-driven index system for field-scale studies.

Groundwater Hydrogeochemical Processes and Potential Threats to Human Health in Fengfeng Coal Mining Area, China

The Fengfeng mining area is in the transition zone between the North China Plain and the Taihang Mountains, and groundwater is the main source of water supply in the district. Under the combined influence of human activities and natural geological conditions, the quality of different types of groundwater varies greatly, posing a potential threat to the safety of drinking water. In this study, hydrogeochemical processes in different types of groundwater were analyzed using multivariate statistical analysis methods with ion–ratio relationships, and a groundwater quality and health risk assessment model was developed. The research findings show that the main chemical components and TDS in the groundwater have obvious spatial distribution characteristics, i.e., the content of deep karst water (DKW) in the west is significantly lower than that of shallow pore water (SPW) in the east, and the hydrochemical type has changed from HCO3–Ca to SO4–Ca. The chemical components of SPW and DKW are mainly derived from silicates and carbonates, accompanied by weathering dissolution of sulphidic minerals, especially SPW. The chemical components of the groundwater was also influenced by the cation exchange reaction and human activities. The quality of the SPW was significantly worse than that of the DKW, and the nitrates in SPW carry a high non-carcinogenic risk, especially to children. The shallow pore water is not suitable for drinking water. This study can provide guidance on the safety of drinking water in the Fengfeng coal mining area and other areas with intensive industrial, mining, and agricultural activities.

Action Quality Assessment Model Using Specialists' Gaze Location and Kinematics Data-Focusing on Evaluating Figure Skating Jumps.

Action quality assessment (AQA) tasks in computer vision evaluate action quality in videos, and they can be applied to sports for performance evaluation. A typical example of AQA is predicting the final score from a video that captures an entire figure skating program. However, no previous studies have predicted individual jump scores, which are of great interest to competitors because of the high weight of competition. Despite the presence of unnecessary information in figure skating videos, human specialists can focus and reduce information when they evaluate jumps. In this study, we clarified the eye movements of figure skating judges and skaters while evaluating jumps and proposed a prediction model for jump performance that utilized specialists' gaze location to reduce information. Kinematic features obtained from the tracking system were input into the model in addition to videos to improve accuracy. The results showed that skaters focused more on the face, whereas judges focused on the lower extremities. These gaze locations were applied to the model, which demonstrated the highest accuracy when utilizing both specialists' gaze locations. The model outperformed human predictions and the baseline model (RMSE:0.775), suggesting a combination of human specialist knowledge and machine capabilities could yield higher accuracy.

Aggregation Methods Based on Quality Model Assessment for Federated Learning Applications: Overview and Comparative Analysis

Federated learning (FL) offers the possibility of collaboration between multiple devices while maintaining data confidentiality, as required by the General Data Protection Regulation (GDPR). Though FL can keep local data private, it may encounter problems when dealing with non-independent and identically distributed data (non-IID), insufficient local training samples or cyber-attacks. This paper introduces algorithms that can provide a reliable aggregation of the global model by investigating the accuracy of models received from clients. This allows reducing the influence of less confident nodes, who were potentially attacked or unable to perform successful training. The analysis includes the proposed FedAcc and FedAccSize algorithms, together with their new extension based on the Lasso regression, FedLasso. FedAcc and FedAccSize set the confidence in each client based only on local models’ accuracy, while FedLasso exploits additional details related to predictions, like predicted class probabilities, to support a refined aggregation. The ability of the proposed algorithms to protect against intruders or underperforming clients is demonstrated experimentally using testing scenarios involving independent and identically distributed (IID) data as well as non-IID data. The comparison with the established FedAvg and FedAvgM algorithms shows that exploiting the quality of the client models is essential for reliable aggregation, which enables rapid and robust improvement in the global model.

Fulmqa: a fuzzy logic-based model for social media data quality assessment

Fulmqa: a fuzzy logic-based model for social media data quality assessment

PROJECT TEAM MANAGEMENT MODEL UNDER RISK CONDITIONS

The paper examines the state of the problem of the influence of risks on the project team's work process. The processes of the team's work during the implementation of the project sprint are defined. The authors identified risk factors that affect the effectiveness of the project team. An analysis of modern approaches was carried out and three directions were identified, which represent the research of project team management processes under conditions of risk. A comprehensive reference model of project team management under risk conditions is proposed in the form of a framework. It reflects the interrelationship of four models: the project team behavior model, the model for assessing the quality of the formation of sprint tasks, the model for determining the distribution of tasks in the project team, and the model for the formation of recommendations. The project team evaluates the text description of the task, obtained from the information system, using the sprint task formation quality assessment model. Natural language processing methods are used to create a model for evaluating the quality of forming sprint tasks, which combine the method of processing text information and the method of learning based on precedents, which allows taking into account the previous experience of the team and its behavior. The project team behavior model allows taking into account the risks of irrational work organization during the sprint. The behavior of the project team is analyzed using Process Mining methods. The case representation model allows the project team to store and reuse knowledge and experience based on simulation modeling and reinforcement learning approaches. It allows the team to determine and evaluate possible options for the distribution of tasks and resources in the team in accordance with the reduction of possible risks. The central element of the proposed framework is the model of recommendations used in decision-making. It provides the project team with the necessary information for effective decision-making in terms of risks in project management. The proposed framework provides an opportunity to reduce the impact of the risks of non-fulfillment of project tasks during the sprint. Further studies of the task of managing the project team under conditions of risk should be directed to the development of specified models of the proposed framework

Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training

Image quality assessment (IQA) is very important for both end-users and service providers since a high-quality image can significantly improve the user's quality of experience (QoE) and also benefit lots of computer vision algorithms. Most existing blind image quality assessment (BIQA) models were developed for synthetically distorted images, however, they perform poorly on in-the-wild images, which are widely existed in various practical applications. In this paper, we propose a novel BIQA model for in-the-wild images by addressing two critical problems in this field: how to learn better quality-aware feature representation, and how to solve the problem of insufficient training samples in terms of their content and distortion diversity. Considering that perceptual visual quality is affected by both low-level visual features (e.g. distortions) and high-level semantic information (e.g. content), we first propose a staircase structure to hierarchically integrate the features from intermediate layers into the final feature representation, which enables the model to make full use of visual information from low-level to high-level. Then an iterative mixed database training (IMDT) strategy is proposed to train the BIQA model on multiple databases simultaneously, so the model can benefit from the increase in both training samples and image content and distortion diversity and can learn a more general feature representation. Experimental results show that the proposed model outperforms other state-of-the-art BIQA models on six in-the-wild IQA databases by a large margin. Moreover, the proposed model shows an excellent performance in the cross-database evaluation experiments, which further demonstrates that the learned feature representation is robust to images with diverse distortions and content. The code is available at https://github.com/sunwei925/StairIQA.

Prior Knowledge-guided Hierarchical Action Quality Assessment with 3D Convolution and Attention Mechanism

Recently, there has been a growing interest in the field of computer vision and deep learning regarding a newly emerging problem known as action quality assessment (AQA). However, most researchers still rely on the traditional approach of using models from the video action recognition field. Unfortunately, this approach overlooks crucial features in AQA, such as movement fluency and degree of completion. Alternatively, some researchers have employed the transformer paradigm to capture action details and overall action integrity, but the high computational cost associated with transformers makes them impractical for real-time tasks. Due to the diversity of action types, it is challenging to rely solely on a shared model for quality assessment of various types of actions. To address these issues, we propose a novel network structure for AQA, which is the first to integrate multi-model capabilities through a classification model. Specifically, we utilize a pre-trained I3D model equipped with a self-attention block for classification. This allows us to evaluate various categories of actions using just one model. Furthermore, we introduce self-attention mechanisms and multi-head attention into the traditional convolutional neural network. By systematically replacing the last few layers of the conventional convolutional network, our model gains a greater ability to sense the global coordination of different actions. We have verified the effectiveness of our approach on the AQA-7 dataset. In comparison to other popular models, our model achieves satisfactory performance while maintaining a low computational cost.

Quality assessment of intelligent physical education teaching in universities based on multivariate statistical analysis and regression analysis

Abstract In this paper, we first propose the basic technical support and service and management of university intelligent physical education composition, and on this basis, we propose a teaching quality assessment model based on multivariate statistical analysis and regression analysis. Among them, multivariate statistical analysis is used to calculate the factor loadings A of physical education teaching, and multiple linear regression is used to establish the teaching quality assessment model and test it. Finally, an empirical analysis of teaching quality assessment was conducted with smart physical education as an example. The results show that the comprehensive assessment value of smart physical education teaching quality based on a multiple linear regression model is very close to the actual value, and the error value ranges from [0.003 to 0.027]. The error values are smaller than [0.0135~0.0921] of the ANN model and [0.0635~0.1033] of the neural network model. The research in this paper can provide scientific quality assessment methods and theoretical support for smart physical education in colleges and universities to promote the development of smart physical education and improve teaching quality in colleges and universities.

Blind Image Quality Assessment for Pathological Microscopic Image under Screen and Immersion Scenarios.

The high-quality pathological microscopic images are essential for physicians or pathologists to make a correct diagnosis. Image quality assessment (IQA) can quantify the visual distortion degree of images and guide the imaging system to improve image quality, thus raising the quality of pathological microscopic images. Current IQA methods are not ideal for pathological microscopy images due to their specificity. In this paper, we present deep learning-based blind image quality assessment model with saliency block and patch block for pathological microscopic images. The saliency block and patch block can handle the local and global distortions, respectively. To better capture the area of interest of pathologists when viewing pathological images, the saliency block is fine-tuned by eye movement data of pathologists. The patch block can capture lots of global information strongly related to image quality via the interaction between different image patches from different positions. The performance of the developed model is validated by the home-made Pathological Microscopic Image Quality Database under Screen and Immersion Scenarios (PMIQD-SIS) and cross-validated by the five public datasets. The results of ablation experiments demonstrate the contribution of the added blocks. The dataset and the corresponding code are publicly available at: https://github.com/mikugyf/PMIQD-SIS.

Innovative Research on Translation Quality Assessment Models in the New Era

Innovative Research on Translation Quality Assessment Models in the New Era

Attention-Aware Patch-Based CNN for Blind 360-Degree Image Quality Assessment.

An attention-aware patch-based deep-learning model for a blind 360-degree image quality assessment (360-IQA) is introduced in this paper. It employs spatial attention mechanisms to focus on spatially significant features, in addition to short skip connections to align them. A long skip connection is adopted to allow features from the earliest layers to be used at the final level. Patches are properly sampled on the sphere to correspond to the viewports displayed to the user using head-mounted displays. The sampling incorporates the relevance of patches by considering (i) the exploration behavior and (ii) a latitude-based selection. An adaptive strategy is applied to improve the pooling of local patch qualities to global image quality. This includes an outlier score rejection step relying on the standard deviation of the obtained scores to consider the agreement, as well as a saliency to weigh them based on their visual significance. Experiments on available 360-IQA databases show that our model outperforms the state of the art in terms of accuracy and generalization ability. This is valid for general deep-learning-based models, multichannel models, and natural scene statistic-based models. Furthermore, when compared to multichannel models, the computational complexity is significantly reduced. Finally, an extensive ablation study gives insights into the efficacy of each component of the proposed model.