Noise-Filtering Enhanced Deep Cognitive Diagnosis Model for LatentSkill Discovering

Educational data mining based on student cognitive diagnosis analysis can provide an important decision basis for personalized learning tutoring of students,which has attracted extensive attention from scholars at home and abroad and has made a series of important research progress.To this end,we propose a noise-filtering enhanced deep cognitive diagno-sis method to improve the fitting ability of traditional models and obtain students’skill mastery status by mining the interaction between students and problems nonlinearly through neural networks.First,modeling complex interactions between students and problems with multidimensional features based on cognitive processing theory can enhance the interpretability of the proposed model;second,the neural network is used to predict students’learning performance,diagnose students’skill mastery and provide immediate feedback;finally,by comparing the proposed model with several baseline models,extensive experimental results on real data sets demonstrate that the proposed Finally,by comparing the proposed model with several baseline models,the extensive experimental results on the actual data set demon-strate that the proposed model not only improves the accuracy of predicting students’learning performance but also enhances the interpretability of the neurocognitive diagnostic model.

New development of cognitive diagnosis models

Cognitive diagnosis is the judgment of the student’s cognitive ability, is a wide-spread concern in educational science. The cognitive diagnosis model (CDM) is an essential method to realize cognitive diagnosis measurement. This paper presents new research on the cognitive diagnosis model and introduces four individual aspects of probability-based CDM and deep learning-based CDM. These four aspects are higher-order latent trait, polytomous responses, polytomous attributes, and multilevel latent traits. The paper also sorts on the contained ideas, model structures and respective characteristics, and provides direction for developing cognitive diagnosis in the future.

A Probabilistic Framework for Temporal Cognitive Diagnosis in Online Learning Systems

Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge concepts.Most existing studies rely on the assumption of static student states and ig-nore the dynamics of proficiency in the learning process,which makes them unsuitable for online learning scenarios.In this paper,we propose a unified temporal item response theory(UTIRT)framework,incorporating temporality and random-ness of proficiency evolving to get both accurate and interpretable diagnosis results.Specifically,we hypothesize that stu-dents'proficiency varies as a Wiener process and describe a probabilistic graphical model in UTIRT to consider temporali-ty and randomness factors.Furthermore,based on the relationship between student states and exercising answers,we hy-pothesize that the answering result at time k contributes most to inferring a student's proficiency at time k,which also re-flects the temporality aspect and enables us to get analytical maximization(M-step)in the expectation maximization(EM)algorithm when estimating model parameters.Our UTIRT is a framework containing unified training and inferenc-ing methods,and is general to cover several typical traditional models such as Item Response Theory(IRT),multidimen-sional IRT(MIRT),and temporal IRT(TIRT).Extensive experimental results on real-world datasets show the effective-ness of UTIRT and prove its superiority in leveraging temporality theoretically and practically over TIRT.

Study of Priority Recommendation Method Based on Cognitive Diagnosis Model

In the context of personalized learning,the recommendation method aims to provide appropriate exercises for each student.And individualized knowledge status may give more effective recommendation.In this study,a priority recommendation method based on cognitive diagnosis model is proposed,and cosine similarity algorithm is applied to improve the accuracy and interpretability of recommendation.Then the performance of the methods was compared under cognitive diagnosis models.The experimental results show that the method proposed achieves more accurate results and better performance.

Learning Behavior-Aware Cognitive Diagnosis for Online Education Systems

Cognitive diagnosis,which aims to diagnose students’knowledge proficiency,is crucial for numerous online education applications,such as personalized exercise recommendation.Existing methods in this area mainly exploit students’exercising records,which ignores students’full learning process in online education systems.Besides,the latent relation of exercises with course structure and texts is still underexplored.In this paper,a learning behavior-aware cognitive diagnosis(LCD)framework is proposed for students’cognitive modeling with both learning behavior records and exercising records.The concept of LCD was first introduced to characterize students’knowledge proficiency more completely.Second,a course graph was designed to explore rich information existed in course texts and structures.Third,an interaction function was put forward to explore complex relationships between students,exercises and videos.Extensive experiments on a real-world dataset prove that LCD predicts student performance more effectively,the output of LCD is also interpretable.

Diagnosis advances in vascular cognitive impairment

Vascular cognitive impairment（VCI） encompasses the entire range of cognitive deficits associated with cerebrovascular disease（CVD）, from mild deficits with little or no functional impairment, such as vascular cognitive impairment-no dementia（VCIND）, to full-blown vascular dementia（VaD）. Accurate diagnosis of vascular cognitive impairment is important but may be difficult. In this review we report advances in VCI in the following areas： etiology, subtypes, neuropsychology, biomarkers, neuroimaging, and diagnostic criteria.

Module Diagnostic-Training System An Innovative Solution for Diagnosis and Assessment of Cognitive Processes

The development of cognitive competences for police officers and other officers of the uniformed services is crucial The Police Academy in Szczytno （Poland） developed--as part of a research and development project （2013-2015）---an innovative diagnostic system for training that allows automated assessment of the current fitness level of cognitive functions and their online training. The system consists of three interconnected modules： diagnostic module, training module, and knowledge base. It is a fully functional online platform. Various forms of cognitive training in the form of games have been proposed. The system includes a component in the form of a psychophysiological recorder, which is intended for the training of coping with stress. The innovativeness of this diagnostic training system involves the use of information systems to stimulate the cognitive competence of officers by designing exercises in the form of computer games and to permit to verify their current mental shapes. It is assumed that this solution will develop the personal skills of officers and positively affect their operational readiness. Extending the area of application of this diagnostic training module by other functionalities can contribute to improving the effectiveness and safety of work, especially in occupational groups performing tasks requiring special cognitive and psychomotor predispositions.

The Application of Scales in the Diagnosis of Perceived Needs in the Elderly with Mild Cognitive Impairment

The study evaluated the use of the Mini-Mental State Examination scale (MMSE), Tinettiscale, and Motor Scale for the Elderly (EMTI) toassist in the diagnosis of potential needs observed in elderlies with Mild Cognitive Impairment. This was aquasi-experimental research, conducted in a Basic Health Unit in thecityof Rio de Janeiro in 2014. The sample population consisted of 22 elderlies aged 64 to 88 years and 86.36% females. The SAS statistical software (version 9.3.1) and Kruskal-Wallis test were used at a 95% confidence interval and a significance level of 0.05 and demonstrated significant differences in the evaluations performed before and after the intervention. The detected diagnoses were: impaired memory, the risk of falls, and willingness to improved relationships, among others. The evaluations showed MMSE results that were suggestive of cognitive impairment in 22.73% of the elderlies;the Tinetti scale showed a high risk of falls in 31.82% of theelderlies;and EMTI with 88.36 points, which was equivalent to the normal low classification. The intervention took place through ten weekly activity sessions after the initial evaluations. In the second evaluation, the Tinetti showed 59.09% of the elderlies with a moderate risk of falls and the EMTI as the normal average classification with 90.32 points. It was concluded that the scales offered diagnostic possibilities, which allowed for the implementation of necessary interventions according to the detected problems.

Detection of cognitive impairment in patients with obstructive sleep apnea hypopnea syndrome using mismatch negativity

In this experiment, 97 patients with obstructive sleep apnea hypopnea syndrome were divided into three groups （mild, moderate, severe） according to minimum oxygen saturation, and 35 healthy subjects were examined as controls. Cognitive function was determined using the mismatch negativity paradigm and the Montreal Cognitive Assessment. The results revealed that as the disease worsened, the mismatch negativity latency was gradually extended, and the amplitude gradually declined in patients with obstructive sleep apnea hypopnea syndrome. Importantly, mismatch negativity latency in severe patients with a persistent time of minimum oxygen saturation 〈 60 seconds was significantly shorter than that with a persistent time of minimum oxygen saturation 〉 60 seconds. Correlation analysis revealed a negative correlation between minimum oxygen saturation latency and Montreal Cognitive Assessment scores. These findings indicate that intermittent night-time hypoxemia affects mismatch negativity waveforms and Montrea Cognitive Assessment scores. As indicators for detecting the cognitive functional status of obstructive sleep apnea hypopnea syndrome patients, the sensitivity of mismatch negativity is 82.93%, the specificity is 73.33%, the accuracy rate is 81.52%, the positive predictive value is 85.00%, the negative predictive value is 70.21%, the positive likelihood ratio is 3, and the negative likelihood ratio is 0.23. These results indicate that mismatch negativity can be used as an effective tool for diagnosis of cognitive dysfunction in obstructive sleep apnea hypopnea syndrome patients.

Fault diagnosis using noise modeling and a new artificial immune system based algorithm

A new fault classification/diagnosis method based on artificial immune system (AIS) algorithms for the structural systems is proposed. In order to improve the accuracy of the proposed method, i.e., higher success rate, Gaussian and non-Gaussian noise generating models are applied to simulate environmental noise. The identification of noise model, known as training process, is based on the estimation of the noise model parameters by genetic algorithms (GA) utilizing real experimental features. The proposed fault classification/diagnosis algorithm is applied to the noise contaminated features. Then, the results are compared to that obtained without noise modeling. The performance of the proposed method is examined using three laboratory case studies in two healthy and damaged conditions. Finally three different types of noise models are studied and it is shown experimentally that the proposed algorithm with non-Gaussian noise modeling leads to more accurate clustering of memory cells as the major part of the fault classification procedure.

Diagnostic delay in oral squamous cell carcinoma: the role of cognitive and psychological variables

This retrospective study investigated, in two cohorts of subjects living in Southern Italy and awaiting treatment for oral squamous cell carcinoma （OSCC）, the variables related to diagnostic delay ascribable to the patient, with particular reference to the cognitive and psychological ones. A total of 156 patients with OSCC （mean age： 62 years, M/F： 2.39 ： 1） were recruited at the Universities of Palermo and Naples. Risk factors related to patient delay included： sociodemographic, health-related, cognitive and psychological variables. The analysis was conducted by considering two different delay ranges： dichotomous （≤1 month vs. 〉 1 month） and polytomous （〈1 month, 1-3 months, 〉3 months） delay. Data were investigated by univariate and multivariate analyses and a Pvalue≤0.05 was considered statistically significant. For both delay measurements, the most relevant variables were： ＇Personal experience of cancer＇ （dichotomous delay： P=0.05, odds ratio （0R）=0.33, 95% confidence interval （CI）=0. 11-0.99; polytomous delay： P=0.006, Chi-square= 10.224） and ＇Unawareness＇ （dichotomous delay： P〈0.01, 0R=4.96, 95% CI--2.16-11.37; polytomous delay： P=0.087, Chi-square=4.77）. Also ＇Denial＇ （P〈0.01, 0R=6.84, 95% CI=2.31-20.24） and ＇Knowledge of cancer＇ （P=0.079, Chi-square=8.359） were found to be statistically significant both for dichotomous and for polytomous categorization of delay, respectively. The findings of this study indicated that, in the investigated cohorts, the knowledge about cancer issues is strongly linked to the patient delay. Educational interventions on the Mediterranean population are necessary in order to increase the patient awareness and to emphasize his/her key role in early diagnosis of OSCC.

Proteomics of serum exosomes identified fibulin-1 as a novel biomarker for mild cognitive impairment

Mild cognitive impairment(MCI)is a prodrome of Alzheimer’s disease pathology.Cognitive impairment patients often have a delayed diagnosis because there are no early symptoms or conventional diagnostic methods.Exosomes play a vital role in cell-to-cell communications and can act as promising biomarkers in diagnosing diseases.This study was designed to identify serum exosomal candidate proteins that may play roles in diagnosing MCI.Mass spectrometry coupled with tandem mass tag approach-based non-targeted proteomics was used to show the differentially expressed proteins in exosomes between MCI patients and healthy controls,and these differential proteins were validated using immunoblot and enzyme-linked immunosorbent assays.Correlation of cognitive performance with the serum exosomal protein level was determined.Nanoparticle tracking analysis suggested that there was a higher serum exosome concentration and smaller exosome diameter in individuals with MCI compared with healthy controls.We identified 69 exosomal proteins that were differentially expressed between MCI patients and healthy controls using mass spectrometry analysis.Thirty-nine exosomal proteins were upregulated in MCI patients compared with those in control patients.Exosomal fibulin-1,with an area under the curve value of 0.81,may be a biomarker for an MCI diagnosis.The exosomal protein signature from MCI patients reflected the cell adhesion molecule category.In particular,higher exosomal fibulin-1 levels correlated with lower cognitive performance.Thus,this study revealed that exosomal fibulin-1 is a promising biomarker for diagnosing MCI.

Novel Computer-Aided Diagnosis System for the Early Detection of Alzheimer’s Disease

Aging is a natural process that leads to debility,disease,and dependency.Alzheimer’s disease(AD)causes degeneration of the brain cells leading to cognitive decline and memory loss,as well as dependence on others to fulfill basic daily needs.AD is the major cause of dementia.Computer-aided diagnosis(CADx)tools aid medical practitioners in accurately identifying diseases such as AD in patients.This study aimed to develop a CADx tool for the early detection of AD using the Intelligent Water Drop(IWD)algorithm and the Random Forest(RF)classifier.The IWD algorithm an efficient feature selection method,was used to identify the most deterministic features of AD in the dataset.RF is an ensemble method that leverages multiple weak learners to classify a patient’s disease as either demented(DN)or cognitively normal(CN).The proposed tool also classifies patients as mild cognitive impairment(MCI)or CN.The dataset on which the performance of the proposed CADx was evaluated was sourced from the Alzheimer’s Disease Neuroimaging Initiative(ADNI).The RF ensemble method achieves 100%accuracy in identifying DN patients from CN patients.The classification accuracy for classifying patients as MCI or CN is 92%.This study emphasizes the significance of pre-processing prior to classification to improve the classification results of the proposed CADx tool.

认知诊断评估中Q矩阵理论及应用

Q矩阵是认知心理学与心理计量学结合的重要载体,Q矩阵在认知诊断中发挥着十分重要的作用。Q矩阵理论和应用研究近年来取得了重要进展。众多研究者从结构化到非结构化、属性二值到多值、简单到复杂模型、独立到一般结构、0-1到多级评分方面不断深入和拓展Q矩阵理论。Q矩阵理论也广泛应用于测验构念效度评价、计算机化自适应测验选题策略设计、Q矩阵学习和标定、认知诊断测验组卷等。与模型无关的Q矩阵理论和适合特定认知诊断模型下Q矩阵理论,以及最新Q矩阵理论的应用都值得深入研究。

基于SOM神经网络的教学认知诊断模型研究

认知诊断模型在评估知识点依赖关系松散型学科知识状态时,因其生成的可达矩阵较为稀疏,易导致认知诊断的效率和准确度降低。而自组织映射(Self-Organizing Maps,SOM)神经网络可在不考虑知识点依赖关系的情况下,通过自动发现样本中的内在规律和本质属性,实现对学生知识状态的分类与评估。基于此,文章构建了基于SOM神经网络的教学认知诊断模型,在“大学英语视听说”课程中开展了此诊断模型的教学应用,并从诊断结果、学习成效、满意度三个方面进行了应用效果分析,结果表明:诊断模型用于知识点依赖关系松散型学科时,能够通过自组织聚类消除学生答题过程中的误差,精准、高效地分类评估学生的知识状态;诊断模型有助于教师实施有针对性的补救教学,在提高学生的学习效率和避免成绩的两极化方面效果显著;学生对诊断模型的整体满意度也较高。文章的研究丰富了教学认知诊断理论,可为个性化学习、精准补救教学提供诊断方法和实践经验。

认知诊断评价中的被试拟合研究

通常情况下,认知诊断需要通过认知诊断模型对被试进行诊断评价。认知诊断模型所生成诊断结果的有效性依赖于被试作答反应是否与所选用的模型拟合。因此,在对诊断结果进行评估的时候,需要通过被试拟合分析来对被试个体的作答反应与模型的拟合情况进行检验,以避免错误或无效的补救措施。本研究基于加权的得分残差,提出认知诊断评价中新的被试拟合指标R。模拟研究结果表明,R指标的一类错误率有较好的稳定性,对随机作答、疲劳、睡眠和创造性作答四种异常被试类型均有较高的统计检验力。并将R指标应用于分数减法实证数据,展示指标在实际测验中的使用过程。

重视PET成像在帕金森病认知功能障碍早期诊断的价值

帕金森病(PD)是仅次于阿尔茨海默病的第二大神经退行性疾病,严重危害人们的生命健康,给社会和家庭带来巨大负担。PD认知功能障碍主要包括PD轻度认知损害和PD痴呆。随着不同PET靶向示踪剂的发展,目前PET成像技术已经成为评估PD患者认知功能障碍的重要分子影像手段,对早期诊断具有重要价值。

基于知识关系与试题价值权重的认知诊断模型

现有认知诊断方法忽略了试题中知识点之间存在的显性、隐性相关性以及试题的价值权重,为解决上述问题,文章提出了一种基于神经网络的诊断模型(QENCD)。该模型首先利用Jaccard算法探索知识点间的相似性,发现试题中的显性知识点,并根据特征向量中心性算法求其权重;其次,利用显性知识点信息作为先验信息来推断试题中的隐性知识点;然后,引入学生潜能因素和试题价值权重因素,重新构建交互函数;最后,结合猜测因素预测学生是否能正确回答试题,了解学生实际水平。在4个真实数据集(ASSIST0910、MathEC、Junyi和Math1)上,将QENCD模型与3个统计认知诊断模型(IRT、MIRT、DINA)、3个神经网络认知诊断模型(NCD、CDGK、ICD)进行对比实验;同时,为了验证每个组件的有效性,进行了消融试验,通过移除模型的不同部分(如知识矩阵、试题价值权重等)来评估各部分对模型性能的影响。此外,进行了基于一致性程度指标(DOA)的可解释性实验,以衡量模型的解释能力。对比实验结果表明在4个真实数据集上,与目前最佳的基线模型(ICD)相比,QENCD模型的ACC、AUC平均提高了0.84%、1.12%,RMSE降低了0.38%。消融实验结果显示:模型的不同部分对模型的准确性和解释性都有重要贡献。由4个模型(DINA、NCDM、CDGK和QENCD)在4个真实数据集上的DOA值可知:QENCD模型能够更准确地识别和解释学生的知识状态。

体验认知观下研究生科学研究能力及素养的培养——以语言学研究方法课程为例

本研究从体验认知教学理念出发,紧贴语言学研究实施步骤,充分发挥实践体验的能动作用,通过创新英语语言学研究方法课程模式,培养研究生从发现问题、设计研究、实践方法,到独立思考、解决问题并呈现研究结果的能力。实验教学在课程满意度、丰富度、科学性及课程思政等方面取得了理想效果。研究在探索培养英语专业研究生学术研究能力及素养的专业课程模式,创新外语人才培养理念,使学生具备科学、严谨、规范的研究意识和独立开展科学研究的能力方面进行了有益尝试。

健听儿童“把”字句习得的体认识解及其早期诊断与干预价值

健听儿童在6岁前已习得9种类型的“把”字句,接近成人“把”字句使用情况。健听儿童通过与客观世界的互动体验和认知加工,在头脑中建立事件域认知模型,该模型以动作和事体为核心要素,儿童以动作和事体构成的事件域为单位体认现实生活。再结合物理空间、人体空间、时间、社会空间等层面的空间位移认知图式,形成不同类型的“把”字句。对健听儿童“把”字句习得机制的认识有助于言语障碍儿童的早期诊断与干预。