Quality Assessment Model Research Articles

A LIBSVM quality assessment model for apple spoilage during storage based on hyperspectral data.

To assess the quality of apple samples during storage, this study proposes a spoilage benchmark based on hyperspectral data feature indicators and the Mahalanobis Distance (MD). Additionally, a quality assessment model was developed utilizing LIB Support Vector Machine (LIBSVM). Initially, a spoilage benchmark for apple samples was preliminarily established using hyperspectral data feature indicators, including the color feature, texture feature of sample hyperspectral images, and wavelet packet energy (WPE) of sample spectral information. Secondly, this study utilized the successive projection algorithm (SPA) to extract three wavelength sets sensitive to changes in the three indicators. This process resulted in the identification of 20 feature wavelengths based on the three sets. Subsequently, the spoilage benchmark for apple samples was verified using MD based on the spectral information of feature wavelengths. Ultimately, utilizing pre-processed spectral information enhanced by the sliding window algorithm and spoilage benchmark, the LIBSVM quality assessment model was developed, achieving a training set accuracy of 99.94% and a test set accuracy of 99.66%. Moreover, to assess the strength and applicability of the model, a verification experiment was conducted using a different set of apple samples. The training set accuracy was 100% and the test set accuracy was 99.83%. These findings indicate that the model can effectively indicate the level of spoilage in each sample during long-term storage. This also serves to demonstrate the robustness of the model and the effectiveness of the spoilage benchmark determination method during apple storage.

A data mining-based model for comprehensive assessment of English teaching quality of university students

A data mining-based model for comprehensive assessment of English teaching quality of university students

2AFC Prompting of Large Multimodal Models for Image Quality Assessment

2AFC Prompting of Large Multimodal Models for Image Quality Assessment

A Dataset and Model for the Visual Quality Assessment of Inversely Tone-Mapped HDR Videos.

To enhance the viewer experience of standard dynamic range (SDR) video content on high dynamic range (HDR) displays, inverse tone mapping (ITM) is employed. Objective visual quality assessment (VQA) models are needed for effective evaluation of ITM algorithms. However, there is a lack of specialized VQA models for assessing the visual quality of inversely tone-mapped HDR videos (ITM-HDR-Videos). This paper addresses both an algorithmic and a dataset gap by introducing a novel SDR referenced HDR (SD-R-HD) VQA model tailored for ITM-HDR-Videos, along with the first public dataset specifically constructed for this purpose. The innovations of the SD-R-HD VQA model include 1) utilizing available SDR video as a reference signal, 2) extracting features that characterize standard ITM operations such as global mapping and local compensation, and 3) directly modeling interframe inconsistencies introduced by ITM operations. The newly created ITM-HDR-VQA dataset comprises 200 ITM-HDR-Videos annotated with mean opinion scores, gathered over 320 man-hours of psychovisual experiments. Experimental results demonstrate that the SD-R-HD VQA model significantly outperforms existing state-of-the-art VQA models.

Construction of qualitative assessment model of ecological environment quality under river safety remediation

Construction of qualitative assessment model of ecological environment quality under river safety remediation

Construction of qualitative assessment model of ecological environment quality under river safety remediation

Construction of qualitative assessment model of ecological environment quality under river safety remediation

Intelligent Assessment of Teaching Quality of Computer Technology Courses in Colleges and Universities Based on ISSA-DRNN

Abstract With the continuous development of artificial intelligence technology, its application in the teaching of computer technology courses in colleges and universities is gradually deepened. In this study, the traditional sparrow search algorithm (SSA) is first processed to find the optimal solution, and then the ISSA algorithm is proposed and modeled. Training the deep recurrent neural network algorithm (DRNN) and combining it with the ISSA algorithm resulted in the construction of the teaching wisdom assessment model for the course. Finally, a teaching quality evaluation system for computer courses is constructed and applied to explore changes in teaching quality. The results show that in the assessment of the teaching quality of computer technology courses, the course structure and the teacher’s profile occupy the highest weight, and the weights occupied by these two items are more than 0.7. Secondly, the accuracy of the ISSADRNN model reaches more than 95%, and the maximum error is 0.0284. The average scores of each index system are more than 88. The overall performance is good and close to excellent. The model output’s actual value is within the expected range and has high accuracy. It can be seen that the intelligent assessment model of computer teaching quality proposed in this study has broad application potential and practical value.

Quality assessment of radiomics models in carotid plaque: a systematic review.

Although imaging techniques provide information about the morphology and stability of carotid plaque, they are operator dependent and may miss certain subtleties. A variety of radiomics models for carotid plaque have recently been proposed for identifying vulnerable plaques and predicting cardiovascular and cerebrovascular diseases. The purpose of this review was to assess the risk of bias, reporting, and methodological quality of radiomics models for carotid atherosclerosis plaques. A systematic search was carried out to identify available literature published in PubMed, Web of Science, and the Cochrane Library up to March 2023. Studies that developed and/or validated machine learning models based on radiomics data to identify and/or predict unfavorable cerebral and cardiovascular events in carotid plaque were included. The basic information of each piece of included literature was identified, and the reporting quality, risk of bias, and radiomics methodology quality were assessed according the TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) checklist, the Prediction Model Risk of Bias Assessment Tool (PROBAST), and the radiomics quality score (RQS), respectively. A total of 2,738 patients from 19 studies were included. The mean overall TRIPOD adherence rate was 66.1% (standard deviation 12.8%), with a range of 45-87%. All studies had a high overall risk of bias, with the analysis domain being the most common source of bias. The mean RQS was 9.89 (standard deviation 5.70), accounting for 27.4% of the possible maximum value of 36. The mean area under the curve for diagnostic or predictive properties of these included radiomics models was 0.876±0.09, with a range of 0.741-0.989. Radiomics models may have value in the assessment of carotid plaque, the overall scientific validity and reporting quality of current carotid plaque radiomics reports are still lacking, and many barriers must be overcome before these models can be applied in clinical practice.

Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality.

We study the visual quality judgments of human subjects on digital human avatars (sometimes referred to as "holograms" in the parlance of virtual reality [VR] and augmented reality [AR] systems) that have been subjected to distortions. We also study the ability of video quality models to predict human judgments. As streaming human avatar videos in VR or AR become increasingly common, the need for more advanced human avatar video compression protocols will be required to address the tradeoffs between faithfully transmitting high-quality visual representations while adjusting to changeable bandwidth scenarios. During transmission over the internet, the perceived quality of compressed human avatar videos can be severely impaired by visual artifacts. To optimize trade-offs between perceptual quality and data volume in practical workflows, video quality assessment (VQA) models are essential tools. However, there are very few VQA algorithms developed specifically to analyze human body avatar videos, due, at least in part, to the dearth of appropriate and comprehensive datasets of adequate size. Towards filling this gap, we introduce the LIVE-Meta Rendered Human Avatar VQA Database, which contains 720 human avatar videos processed using 20 different combinations of encoding parameters, labeled by corresponding human perceptual quality judgments that were collected in six degrees of freedom VR headsets. To demonstrate the usefulness of this new and unique video resource, we use it to study and compare the performances of a variety of state-of-the-art Full Reference and No Reference video quality prediction models, including a new model called HoloQA. As a service to the research community, we publicly releases the metadata of the new database at https://live.ece.utexas.edu/research/LIVE-Meta-rendered-human-avatar/index.html.

Image Quality Assessment: Measuring Perceptual Degradation via Distribution Measures in Deep Feature Spaces.

This study aims to develop advanced and training-free full-reference image quality assessment (FR-IQA) models based on deep neural networks. Specifically, we investigate measures that allow us to perceptually compare deep network features and reveal their underlying factors. We find that distribution measures enjoy advanced perceptual awareness and test the Wasserstein distance (WSD), Jensen-Shannon divergence (JSD), and symmetric Kullback-Leibler divergence (SKLD) measures when comparing deep features acquired from various pretrained deep networks, including the Visual Geometry Group (VGG) network, SqueezeNet, MobileNet, and EfficientNet. The proposed FR-IQA models exhibit superior alignment with subjective human evaluations across diverse image quality assessment (IQA) datasets without training, demonstrating the advanced perceptual relevance of distribution measures when comparing deep network features. Additionally, we explore the applicability of deep distribution measures in image super-resolution enhancement tasks, highlighting their potential for guiding perceptual enhancements. The code is available on website. (https://github.com/Buka-Xing/Deep-network-based-distribution-measures-for-full-reference-image-quality-assessment).

Deep Feature Statistics Mapping for Generalized Screen Content Image Quality Assessment.

The statistical regularities of natural images, referred to as natural scene statistics, play an important role in no-reference image quality assessment. However, it has been widely acknowledged that screen content images (SCIs), which are typically computer generated, do not hold such statistics. Here we make the first attempt to learn the statistics of SCIs, based upon which the quality of SCIs can be effectively determined. The underlying mechanism of the proposed approach is based upon the mild assumption that the SCIs, which are not physically acquired, still obey certain statistics that could be understood in a learning fashion. We empirically show that the statistics deviation could be effectively leveraged in quality assessment, and the proposed method is superior when evaluated in different settings. Extensive experimental results demonstrate the Deep Feature Statistics based SCI Quality Assessment (DFSS-IQA) model delivers promising performance compared with existing NR-IQA models and shows a high generalization capability in the cross-dataset settings. The implementation of our method is publicly available at https://github.com/Baoliang93/DFSS-IQA.

Deep Learning Model for Quality Assessment of Urinary Bladder Ultrasound Images using Multi-scale and Higher-order Processing.

Autonomous Ultrasound Image Quality Assessment (US-IQA) is a promising tool to aid the interpretation by practicing sonographers and to enable the future robotization of ultrasound procedures. However, autonomous US-IQA has several challenges. Ultrasound images contain many spurious artifacts, such as noise due to handheld probe positioning, errors in the selection of probe parameters and patient respiration during the procedure. Further, these images are highly variable in appearance with respect to the individual patient's physiology. We propose to use a deep Convolutional Neural Network (CNN), USQNet, which utilizes a Multi-scale and Local-to-Global Second-order Pooling (MS-L2GSoP) classifier to conduct the sonographer-like assessment of image quality. This classifier first extracts features at multiple scales to encode the inter-patient anatomical variations, similar to a sonographer's understanding of anatomy. Then, it uses second-order pooling in the intermediate layers (local) and at the end of the network (global) to exploit the second-order statistical dependency of multi-scale structural and multi-region textural features. The L2GSoP will capture the higher-order relationships between different spatial locations and provide the seed for correlating local patches, much like a sonographer prioritizes regions across the image. We experimentally validated the USQNet for a new dataset of the human urinary bladder ultrasound images. The validation involved first with the subjective assessment by experienced radiologists' annotation, and then with state-of-the-art CNN networks for US-IQA and its ablated counterparts. The results demonstrate that USQNet achieves a remarkable accuracy of 92.4% and outperforms the SOTA models by 3 - 14% while requiring comparable computation time.

Online and offline mixed teaching quality assessment method for physical education class based on value assignment method

Abstract The blended teaching mode combines the advantages of online and offline teaching, which can improve the effect of university physical education teaching. The article takes the acquisition path of students’ multidimensional learning behavior data as the entry point, introduces the data preprocessing method after acquiring online learning behavior, and then establishes the online-offline blended teaching quality evaluation index system for physical education classes based on the CIPP model. The subjective and objective weights of the evaluation indexes are solved by using the AHP method and the improved pull-apart grade method, and the comprehensive, integrated assignment method is introduced to weigh the subjective and objective weights in order to obtain the comprehensive weights. Based on the weights of the indicators obtained by AHP-ISD, a teaching quality assessment model for physical education courses was established by combining the SVM model, and the SMO algorithm was selected to optimize the training of the model. To assess the application effectiveness of the model, a comprehensive assessment of its teaching quality was carried out, and the teaching effect of the blended teaching mode was also explored. The weight of the learning outcome evaluation index is 0.438 at most, the accuracy of the SMO algorithm training model is up to 99.99%, and the range of error scores between the model evaluation value and the actual value is between [0.01,0.03] points. The teaching quality assessment model based on the assignment method can obtain more accurate teaching quality assessment results for physical education courses and provide a new direction for optimizing the hybrid teaching assessment method of physical education courses.

3D-PSSIM: Projective Structural Similarity for 3D Mesh Quality Assessment Robust to Topological Irregularities.

Despite acceleration in the use of 3D meshes, it is difficult to find effective mesh quality assessment algorithms that can produce predictions highly correlated with human subjective opinions. Defining mesh quality features is challenging due to the irregular topology of meshes, which are defined on vertices and triangles. To address this, we propose a novel 3D projective structural similarity index ( 3D- PSSIM) for meshes that is robust to differences in mesh topology. We address topological differences between meshes by introducing multi-view and multi-layer projections that can densely represent the mesh textures and geometrical shapes irrespective of mesh topology. It also addresses occlusion problems that occur during projection. We propose visual sensitivity weights that capture the perceptual sensitivity to the degree of mesh surface curvature. 3D- PSSIM computes perceptual quality predictions by aggregating quality-aware features that are computed in multiple projective spaces onto the mesh domain, rather than on 2D spaces. This allows 3D- PSSIM to determine which parts of a mesh surface are distorted by geometric or color impairments. Experimental results show that 3D- PSSIM can predict mesh quality with high correlation against human subjective judgments, across the presence of noise, even when there are large topological differences, outperforming existing mesh quality assessment models.

Air quality assessment model

This study examines the application of machine learning methods to predict air quality in Brisbane, Australia. The main attention is paid to the creation of a model capable of predicting the concentration of PM10 suspended particles based on meteorological data. In the course of the work, a statistical analysis of the factors influencing the level of pollution was carried out, and a random forest model was developed and tested. The results showed that the model is able to explain about 69% of the variation in PM10 concentration, and also identified key meteorological parameters such as air temperature and wind speed that have the greatest impact on the concentration of pollutants. The data obtained can be used to improve the monitoring and management of air quality in cities, which in the future may contribute to reducing the harmful effects of pollution on public health.

Construction and Application of English teaching in vocational colleges Model under Output Orientation

Abstract The basic idea of teaching reform and practice is the teaching mode. This research, which is based on POA, examines how higher vocational English is taught under the direction of a new teaching model and assesses the viability and application of using POA to teach English in vocational institutions. This paper establishes an English teaching in vocational colleges model under POA, which consists of three parts: “driving,” “facilitating,” and “evaluating.”Through the improvement of the BP neural network, this research develops the English teaching in vocational colleges quality assessment model under POA, thereby verifying the efficacy of the model. The changes in students’ English achievement are explored through teaching experiments and the two-sided sigmoid curve. A value of 0.007<0.05 in the paired-sample t-test of the experimental class proves that compared with the traditional English teaching in vocational colleges model, the English teaching in vocational colleges model under POA has a more obvious promotion effect on English achievement. The improved BP neural network model produced quantitative assessments of teaching quality that are mostly in line with actual findings. The model is used to evaluate the quality of English instruction in vocational colleges under POA.

EMDSQA: A Neural Speech Quality Assessment Model with Speaker Embedding

EMDSQA: A Neural Speech Quality Assessment Model with Speaker Embedding

Assessment of e-business instructional quality based on BP neural network in new media environment

Abstract Instructional quality assessment is a systematic project involving a wide range. Restricted and influenced by many factors and conditions. How to accurately and effectively assess the instructional quality of teachers. The determination of the assessment system and method is very important. Some people think that the quality of teaching is “the total of the characteristics of tertiary education that can meet the obvious or implicit needs of individuals, groups, and society. These characteristics are shown through the goals, standards, and achievement levels required by the educated, educators, and social development. In this article, a back propagation neural network (BPNN) is used in classroom instructional quality assessment, and a classroom instructional quality assessment model is constructed. The experimental results of this article show that the accuracy rate of the algorithm based on BPNN reaches 89%, and the learning rate reaches 93%.

Research on the Application of Gray Prediction and BP Neural Network in English-Chinese Translation Quality Assessment

Abstract Gray prediction model and BP neural network are increasingly used in many fields as important prediction and analysis tools. The article first elaborates on the related algorithm of the gray prediction method. It constructs the gray prediction model, then constructs the BP neural network, and builds the gray BP neural network translation quality assessment model through the modeling of the simulation of the artificial neural network, and finally takes eight postgraduate students of translation majors of Beijing Foreign Studies University as the subjects, and the eight students translate two articles with similar word counts and difficulties, and score the translation quality of the subjects, and reasonably evaluate and scientifically predict these translations in order to validate the grey translation quality of subjects. The quality of translation is scored, and these translations are reasonably evaluated and scientifically predicted to verify the role and effect of the gray BP neural network in the quality of English-Chinese translation. The study concludes that the results based on the gray prediction model are that the prediction results are in the error range of 0%–7% compared with the original data, and the overall error is small. The prediction results of the compensatory fuzzy neural network prediction model for all 8 subjects before and after translation were more accurate than those predicted by the traditional fuzzy neural network method, with a good fit to the actual monitoring data and a small relative error. Only one subject out of the 8 spent more time on Chapter B than on Chapter A. Chapter B was more time-consuming than Chapter A. The time spent on Chapter A was more than the time spent on Chapter A. Chapter B was more time-consuming than Chapter A. Chapter B was more time-consuming than Chapter A. One subject spent equal time on both articles. The remaining 6 subjects did not spend as much time on chapter B as they did on chapter A.

Research on the Quality Assessment Model of “Dual-Teacher” Teachers in Higher Vocational Colleges and Universities Based on Big Data Technology

Abstract To further analyze the content of “dual-teacher” teacher team construction in higher vocational colleges and universities, this paper focuses on teacher moral construction, teacher training, assessment and evaluation, and incentives for in-depth investigation. It is clear that higher vocational colleges and universities should distinguish between “dual-teacher” teacher quality assessment and ordinary teacher assessment, and put forward the gradient “dual-teacher” teacher quality team construction. Improve the support vector machine, use the binary tree to propose an evaluation model based on incomplete DBT-SVM, and combine multiple binary classifiers to solve the multi-classification problem of “dual-teacher” teacher quality evaluation. The optimal parameter combinations, i.e., C =28 and γ = 0.0534, are obtained using the kernel function and parameter tuning experiments, and the accuracy of the model prediction results reaches 94.325%, taking the “dual-teacher” teachers in a university in Y province as the specific evaluation object. This shows that the accuracy of this DBT-SVM-based evaluation method of “dual-teacher” teacher quality is good.