Accuracy Assessment Results Research Articles

Risk assessment of bridge construction investigated using random forest algorithm

Bridge construction collapse is one of the most common bridge safety accidents. At present, evaluation results are often affected by the ability and experience of the assessor. Therefore, it is difficult to quickly, accurately and effectively evaluate the risk in the process of bridge construction. Moreover, key factors that can prevent accidents can hardly find from the existing bridge construction safety management and evaluation method. This paper analyzes and classifies the artificial and environmental risk factors that affect the bridge construction stage, and establishes 26 risk factors in 5 categories according to the characteristics of bridge construction and the actual situation of the project. Random forest (RF) algorithm is a non-parametric machine learning method based on decision tree, which does not need to be scored by experts in advance and avoids the influence of subjective factors. Compared with other analysis methods, random forest algorithm has the advantages of accurate and robust risk assessment results. Based on the advantages of random forest algorithm and the characteristics of bridge construction risk, this paper uses random forest algorithm to evaluate the bridge construction risk, and ranks the importance of indicators, and identify the index that has a greater influence on the risk. In order to verify the applicability and feasibility of the proposed method, a typical urban complex pedestrian bridge was taken as an example for actual engineering evaluation and verification. The results obtained are basically consistent with the actual risk assessment results of the pedestrian bridge.

Immersive artificial intelligence technology based on entertainment game experience in simulation of psychological health testing for university students

At present, the mental health problems of college students are becoming more and more prominent, but the existing mental health detection methods have certain limitations. Therefore, the combination of entertainment and game experience with artificial intelligence technology in this paper can provide a more comprehensive and accurate mental health detection scheme. The research designed an immersive entertainment game experience platform, in which artificial intelligence technology was used to detect mental health. The platform is based on emotion recognition algorithms and artificial intelligence interaction technology to assess the level of mental health of users by analyzing their behavior and emotional expression in the game. The results show that immersive artificial intelligence technology based on entertainment and game experience can effectively simulate the mental health state of college students. Compared with traditional mental health assessment methods, this technique has obvious advantages in terms of accuracy and comprehensiveness. Users also showed a high degree of acceptance and participation for this entertaining mental health detection method. This technology can provide students with a more relaxed and interesting mental health assessment experience, and can also provide accurate and comprehensive assessment results, and provide scientific and effective guidance for mental health management and intervention of college students.

A threat assessment method based on correlation-similarity information and three-way decisions in interval intuitionistic fuzzy environment

Threat assessment of targets is a critical component of combat decision-making. Existing threat assessment methods only consider specific dimensions of information. When information is missing or abnormal, they may fail to provide accurate assessment results. Moreover, most methods can only obtain the threat level of targets without providing target threat levels based on the battlefield environment. Therefore, in the context of interval intuitionistic fuzziness, this paper proposes a threat assessment method based on Grey Correlation Analysis and Technique for Order Preference by Similarity to an Ideal Solution (GCA-TOPSIS) and three-way decisions. This method utilizes interval intuitionistic fuzzy entropy to calculate attribute weights. It simultaneously considers information on both similarity and correlation between targets. By introducing grey correlation coefficients to balance the similarity and correlation between targets and the ideal solution, the method computes threat degrees based on the information from both dimensions. Through fuzzy evaluation information, it constructs loss functions, calculates decision thresholds, and thereby determines the threat levels of the targets. This approach is better suited for the complex and dynamic battlefield environment, providing decision-makers with target threat levels. Finally, we conducted simulation experiments under both complete data and data anomaly conditions. The results indicate that when the data noise reaches 0.5 dB, the absolute error of GCA-TOPSIS is only 0.08. When 66.67% of the data is missing, the error is 0.16. In both scenarios, the error is much smaller than that of other threat assessment methods. This demonstrates the method's strong robustness and its suitability for complex battlefields.

Phantom study of augmented reality framework to assist epicardial punctures.

The objective of this study is to evaluate the accuracy of an augmented reality (AR) system in improving guidance, accuracy, and visualization during the subxiphoidal approach for epicardial ablation. An AR application was developed to project real-time needle trajectories and patient-specific 3D organs using the Hololens 2. Additionally, needle tracking was implemented to offer real-time feedback to the operator, facilitating needle navigation. The AR application was evaluated through three different experiments: examining overlay accuracy, assessing puncture accuracy, and performing pre-clinical evaluations on a phantom. The results of the overlay accuracy assessment for the AR system yielded . Additionally, the puncture accuracy utilizing the AR system yielded . During the pre-clinical evaluation on the phantom, needle puncture with AR guidance showed , whereas needle puncture without AR guidance showed . Overall, the AR platform has the potential to enhance the accuracy of percutaneous epicardial access for mapping and ablation of cardiac arrhythmias, thereby reducing complications and improving patient outcomes. The significance of this study lies in the potential of AR guidance to enhance the accuracy and safety of percutaneous epicardial access.

Static Stability Behavior-Based Seismic Damage Endurance Assessment of Long-Span Single-Layer Spherical Lattice Shells

ABSTRACT This paper presents a modified evaluation approach for the structural-capacity-reserve (SCR) based on the static stability behavior of single-layer spherical lattice shells to achieve more accurate assessment results of seismic damage endurance. The SCR index in this paper is calculated by integrating the redefined residual structural capacity (RSC) ratio based on post-earthquake static stability behavior within the range of damage degrees caused by strong earthquakes. Compared with the assessment work for seismic damage endurance in the existing literature, the proposed RSC ratio in this paper could take into account both ultimate load-bearing strength and residual deformation. Additionally, the specific quantitative indicator in the proposed assessment method should also be determined according to whether the residual nodal displacement of the lattice shell after an earthquake exceeds the limit value state specified by the design code. The numerical results in the case study indicate that the residual load-bearing strength of the lattice shell remains relatively constant under the same damage state induced by different earthquakes, with residual deformation significantly impacting the assessment of seismic damage endurance. Thereby, the required RSC can be controlled by reducing the residual nodal displacements of the lattice shell under strong earthquakes to achieve a well-balanced design scheme.

Scenario-Based Land Use and Land Cover Change Detection and Prediction Using the Cellular Automata–Markov Model in the Gumara Watershed, Upper Blue Nile Basin, Ethiopia

Land use and land cover (LULC) change detection and prediction studies are crucial for supporting sustainable watershed planning and management. Hence, this study aimed to detect historical LULC changes from 1985 to 2019 and predict future changes for 2035 (near future) and 2065 (far future) in the Gumara watershed, Upper Blue Nile (UBN) Basin, Ethiopia. LULC classification for the years 1985, 2000, 2010, and 2019 was performed using Landsat images along with vegetation indices and topographic factors. The random forest (RF) machine learning algorithm built into the cloud-based platform Google Earth Engine (GEE) was used for classification. The results of the classification accuracy assessment indicated perfect agreement between the classified maps and the validation dataset, with kappa coefficients (K) of 0.92, 0.94, 0.90, and 0.88 for the LULC maps of 1985, 2000, 2010, and 2019, respectively. Based on the classified maps, cultivated land and settlement increased from 58.60 to 83.08% and 0.06 to 0.18%, respectively, from 1985 to 2019 at the expense of decreasing forest, shrubland and grassland. Future LULC prediction was performed using the cellular automata–Markov (CA–Markov) model under (1) the business-as-usual (BAU) scenario, which is based on the current trend of socioeconomic development, and (2) the governance (GOV) scenario, which is based on the Green Legacy Initiative (GLI) program of Ethiopia. Under the BAU scenario, significant expansions of cultivated land and settlement were predicted from 83.08 to 89.01% and 0.18 to 0.83%, respectively, from 2019 to 2065. Conversely, under the GOV scenario, the increase in forest area was predicted to increase from 2.59% (2019) to 4.71% (2065). For this reason, this study recommends following the GOV scenario to prevent flooding and soil degradation in the Gumara watershed. Finally, the results of this study provide information for government policymakers, land use planners, and watershed managers to develop sustainable land use management plans and policies.

Development and validation of a pharmacogenomics reporting workflow based on the illumina global screening array chip.

Background: Microarrays are a well-established and widely adopted technology capable of interrogating hundreds of thousands of loci across the human genome. Combined with imputation to cover common variants not included in the chip design, they offer a cost-effective solution for large-scale genetic studies. Beyond research applications, this technology can be applied for testing pharmacogenomics, nutrigenetics, and complex disease risk prediction. However, establishing clinical reporting workflows requires a thorough evaluation of the assay's performance, which is achieved through validation studies. In this study, we performed pre-clinical validation of a genetic testing workflow based on the Illumina Global Screening Array for 25 pharmacogenomic-related genes. Methods: To evaluate the accuracy of our workflow, we conducted multiple pre-clinical validation studies. Here, we present the results of accuracy and precision assessments, involving a total of 73 cell lines. These assessments encompass reference materials from the Genome-In-A-Bottle (GIAB), the Genetic Testing Reference Material Coordination Program (GeT-RM) projects, as well as additional samples from the 1000 Genomes project (1KGP). We conducted an accuracy assessment of genotype calls for target loci in each indication against established truth sets. Results: In our per-sample analysis, we observed a mean analytical sensitivity of 99.39% and specificity 99.98%. We further assessed the accuracy of star-allele calls by relying on established diplotypes in the GeT-RM catalogue or calls made based on 1KGP genotyping. On average, we detected a diplotype concordance rate of 96.47% across 14 pharmacogenomic-related genes with star allele-calls. Lastly, we evaluated the reproducibility of our findings across replicates and observed 99.48% diplotype and 100% phenotype inter-run concordance. Conclusion: Our comprehensive validation study demonstrates the robustness and reliability of the developed workflow, supporting its readiness for further development for applied testing.

A COMPARATIVE STUDY OF SATELLITE IMAGE RESOLUTIONS FOR DETECTING PEST DAMAGE IN SUNFLOWER FIELDS

Abstract. The diversity of sensors in remote sensing allows for faster and easier detection of changes and issues across different scales, in contrast to conventional ground-based systems. One of the most important distinguishing features among these sensors is their varying resolutions, contributing to the versatility of remote sensing technologies across diverse environmental applications. In this study, the effectiveness of PlanetScope and Sentinel-2 satellite images with different image resolutions in detecting damage caused by a harmful insect (beet webworm moth - Loxostege sticticalis) in sunflower fields in Lüleburgaz district of Kırklareli in the Trace region was evaluated. Damage rates in sunflower fields were analyzed using various spectral indices (Enhanced Vegetation Index and Chlorophyll Index Green) and spectral transformation (Tasseled Cap Greenness) in conjunction with in situ data. Based on the spectral analysis, the satellite image dated 26 July, which showed the most severe damage, was used in the damage assessment analysis. The damaged areas were compared by classifying both satellite images with the Random Forest algorithm. According to the results of the classification accuracy assessment, PlanetScope satellite imagery showed the highest accuracy, with 90% overall accuracy and 84% Kappa statistics, making it a more suitable sensor choice for agricultural applications.

Mapping and Monitoring of Land Use/Land Cover Transformation Using Geospatial Techniques in Varanasi City Development Region, India

Assessing the dynamics and patterns of Land Use and Land Cover (LULC) and its transformation is an important practice of urban planners and environmentalists for a variety of applications, including land management, urban climate modeling, and sustainability of any urban region. Monitoring changes in LULC using geospatial techniques can help to identify areas at risk for indefensible land use, low-grade environment, and especially for sustainable urban planning. This study aims to analyze the changing pattern, dynamics, and alteration of LULC using Google Earth Engine (GEE) and Machine Learning Applications for the years 1991, 2001, 2011, and 2022 in the Varanasi City Development Region (VCDR). The LULC classification was divided into seven classes using random forest classification, and Landsat-5(TM) and 9(OLI-2) satellite data were used. Saga GIS has been utilized for the detection of LULC change during the 1991-2022 period. For validation of classification results, accuracy assessment was estimated using error matrices and through user, producer, and overall accuracy estimation. The Kappa statistics were applied for the reliability of the accuracy assessment result. As a result, the built-up area increased by 507.8 percent, and other classes like agricultural, barren, fallow land, and vegetation cover rapidly declined and altered into concrete areas over the period. Water bodies and river sand classes have been slightly converted into different classes. The finding explains that 114.8 km2 of fertile agricultural land, 14.81 km2 barren land, and 12.93 km2 of vegetation cover transformed into impervious surface, which is unsustainable and causes various problems like food scarcity, environmental degradation, and low quality of urban life. This study can be a useful guide for urban planners, academicians, and policymakers by providing a scientific background for sustainable urban planning and management of VCDR and other cities as well.

Rapid X-ray fluorescence analysis as a modern alternative to traditional spectral methods in geochemical prospecting

The purpose of the study is to present the research results of the capabilities of modern portable rapid X-ray fluorescence analyzers when solving problems of geological and geochemical prospecting. On example of the applied SciAps X200 analyzer, the metrological indicators for the analysis results by portable instruments have been studied. The accuracy assessment results of analytical studies according to state standard reference samples are shown. Reproducibility of the analysis results is calculated on the basis of samples from promising gold sites of the Bodaibo synclinorium. The method is proved to be of high precision, and measurement errors in many cases are many times lower than the permissible certified values. The reproducibility is shown as 0,5–20 % depending on the element, which in most cases is significantly lower than the methodology permits. The results of interlaboratory comparative tests confirming the comparability of the analytical results of stationary and portable X-ray fluorescence analyzers are presented. For a number of significant elements, the authors have substantiated the lack of need to refine the results of the field rapid X-ray fluorescence analysis using labor-intensive and expensive methods with acid decomposition - atomic emission and atomic absorption spectroscopy. It has been proved that introduction of portable express equipment into geological prospecting works will make it possible to conduct real-time “on site” analytical studies.

A statistical Markov-based password strength meter

Although multi-factor authentication is gaining popularity, password-based authentication remains the most commonly employed method for both online login and data encryption. To help users choose secure passwords, password strength meters (PSMs) are a well-known and important tool. However, many PSMs still use simple rule sets or rely on heuristic results. With the continuous development of password-cracking methods, it is difficult for such PSMs to provide accurate assessment results. In this paper, we present a new PSM based on statistical results from a huge number of leaked passwords. The proposed method has a very simple structure, requires only a small amount of storage space, and succeeds in providing reliable feedback in real time. We also confirm the influence of linguistic features on user-created passwords and, therefore, recommend evaluating passwords based on the users’ language.

Smart colorimetric sensing films based on carboxymethyl cellulose incorporated with a natural pH indicator

This study aimed to combine various natural pH indicators of anthocyanin from Karanda (CA) with anthocyanin from butterfly pea flower (BA) or curcumin (CC) to improve the sensitivity of CA. CA75/BA25 and CA25/CC75 enhanced the sensitivity of the endpoint colour change of CA. A smart colorimetric sensing film was also developed and characterised by loading different natural pH indicators on carboxymethyl cellulose (CMC) films. The addition of different natural pH indicators increased the thickness, elongation, colour (a* and b* values), and contact angle of CMC films (p < 0.05). However, the tensile strength, water vapour permeability, film solubility, light transmission, and L* value decreased when different natural pH indicators were added (p < 0.05). The indicator films demonstrated enhanced antioxidant capacity and thermal stability. The FTIR spectra showed that natural pH indicators were successfully immobilised into the CMC films. Notably, the CMC/CA75/BA25 film was the most sensitive film to changes in volatile ammonia and different pH buffer solutions. The CMC/CA75/BA25 film changed from purple to green with exposure to ammonia solution and from pink to purple to blue to green with increasing pH. Therefore, the CMC/CA75/BA25 film has potential as a colorimetric sensing film, providing a more accurate assessment result.

Validity of Test: English Lecturers perceptions of Test Validity in Intensive Reading Course' Final Exam at Universitas Prima Indonesia in academic year 2022/2023

This study was inspired from the researcher’ effort in order to enrich knowledge related to language testing’ component, one of component is validity and also curiosity to investigate the validity of Intensive Reading Final Test given by English lecturers in University of Prima Indonesia (UNPRI) in academic year 2022/2023. The research addresses two key questions: the lecturers’ perception of test validity in Intensive Reading Final Test in English Education Study Program of Teacher Training and Education Faculty of Universitas Prima Indonesia (UNPRI) and the reason of English lecturers in English Education Study Program of Teacher Training and Education Faculty of Universitas Prima Indonesia (UNPRI) Medan have such perceptions. This study applies qualitative research design in which involving 10 English lecturers at University of Prima Indonesia (UNPRI) as the respondents of this research, analyzing the perception of English lecturers related to validity of test in Intensive Reading Subject Final Exam. Findings shows that lecturers show their positive response to test validity with the information as follows: ALWAYS carry out an analysis of the question items before carrying out the Final Test” is in the percentage of 80%, “FREQUENTLY carry out crosschecks between basic competencies and indicators determined in the questions” is in the percentage of 100 %, “ALWAYS (60 %) and FREQUENTLY (20%) Carry out reliability/consistency measurements (reliability)”, “ALWAYS (60%) Providing feedback on test results given to students. Lecturers take such action in preparing final semester exam questions for Intensive reading courses are: Analyzing test items is crucial in creating effective assessments, Feedback on tests is crucial for students' learning and development, crosschecking between indicators and test items to make sure that educational tests are valid and reliable, the reliability of question items critical for producing accurate, consistent, and trustworthy assessment results. It supports the meaningful interpretation of scores and allows for valid comparisons across individuals or groups. A way to make a high-test validity, it can be done in some ways such as compile the test grid before writing and selecting items to be tested, and making or selecting items on the test based on standard competence, basic competence, learning objectives that have been formulated in the syllabus

Non-interference assessment in colored net systems via integer linear programming

Event-related information leaks are a potential security hazard in information systems. Non-interference is a security property to describe event-related information security. Non-interference assessment is to detect whether a public observer can infer the occurrences of private events from the observation of public ones. To assess the non-interference of information systems, the utilization of formal modeling tools, especially Petri nets (PNs), is an effective way used in most previous works. However, for large-scale systems, non-interference assessment leads to the problem of state explosion in the context of basic net systems (NSs) defined by PNs. In this paper, considering the structural similarity of large-scale systems, colored PNs are used to model them more compactly and efficiently. We focus on the assessment of two typical non-interference properties, i.e., strong nondeterministic non-interference (SNNI) and bisimulation SNNI (BSNNI), in colored NSs (CNSs). Specifically, we propose a non-interference assessment method for bounded CNSs based on the definitions of SNNI and BSNNI in the context of CNSs. This method involves coarse and fine assessments. A coarse assessment is achieved via integer linear programming (ILP) by leveraging the structural similarity of systems. In contrast, the fine assessment can be fulfilled using ILP-based analysis or firing way analysis based on the results obtained by the coarse assessment, which is not essentially necessary. In particular, a fine assessment is necessary only if a coarse assessment is failed to obtain accurate assessment results. Finally, efficiency analysis reveals that our method reduces assessment redundancy and improves assessment efficiency.

Апробация и валидизация методики «Индекс автономного функционирования» (IAF) на российской выборке

&lt;p&gt;One of the key issues in contemporary psychology is a correlation between determinism and indeterminism in understanding human behaviour. Autonomy as self-determined behaviour, as an individual's autonomous choice of behaviour, is one of the most significant and sought-after constructs in the study of personality functioning. In E. Deci and R. Ryan's self-determination theory (SDT), the need for autonomy is one of the basic innate needs of the personality, and this confirms the need for a person to feel as an actor, an initiator, the cause of one's own life and to act in harmony with one's integrated Self. The article presents the procedure of adaptation of the Russian-language version of the &amp;ldquo;Index of Autonomous Functioning&amp;rdquo; (IAF) developed within the macro-theory of self-determination by E. Deci and R. Ryan. The methodology assesses the need for autonomy, including such characteristics as authorship in life, self-interest and susceptibility to external control. In the article we studied the results of reliability and accuracy assessment (Cronbach's coefficient &amp;ndash; 0,774) on a sample of 689 university students in Saint Petersburg. The structure of the questionnaire had three scales: authorship, susceptibility to control, and interest. Correlation analysis confirmed the correlation of the scales with other methods of measuring autonomous behavior, such as "Subjective Quality of Choice", "The Existence Scale", "World Assumptions Scale" and "Stolin Self-Relationship Questionnaire". Testing of diagnostic sensitivity of the Russian version of the questionnaire showed positive results, revealing significant level differences between three clusters: respondents with high, medium and low autonomous functioning index, as well as significant differences in gender and level of education of the respondents. A positive correlation was found between the overall IAF score, the interest-taking subscale, and the age of respondents (within Russian sample). According to the results, the Russian-language version of the &amp;ldquo;Index of Autonomous Functioning&amp;rdquo; has good psychometric characteristics and can be used as a qualitative research tool.&lt;/p&gt;

Research on the steam power system operation condition assessment method based on PCA-AE

The traditional steam power system operation condition assessment method relies on expert knowledge and is difficult to achieve complete objectivity. Most data-driven methods require training models with system anomaly data. In response to the above issues, this article proposes the A Novel PCA-AE Steam Power System Operation Condition Assessment Method. This method utilizes the PCA model to obtain assessment indicator parameters, and uses the Autoencoder to automatically assign weights and reconstruct parameters. Finally, the vector similarity principle is used for quantitative assessment. Based on the simulation data of marine nuclear power system steam turbine and the experimental data of supercharged boiler, the feasibility and generalization ability of this method are verified. The new method can meet the requirements of different steam power systems, including the nuclear power system secondary circuits, and provide accurate quantitative assessment results of operating conditions to guide maintenance work. Meanwhile, this method does not rely on expert knowledge and abnormal data training sets, and has fewer limitations compared to traditional methods.

Comparative study of two cost assessment approaches to models for offshore oil and gas platform decommissioning

Offshore oil and gas facilities have been developed for over a century. The current exploration, development, and mining technologies are already perfect. However, the offshore oil and gas facilities in the world's major offshore oil-producing countries face serious aging challenges and many are overdue for service. Moreover, many oil and gas platforms are in urgent need of decommissioning. The cost of decommissioning is one of the most concerning issues for energy companies and governments. This study compared two different approaches to cost assessment models built by using United Kingdom Continental Shelf (UKCS) decommissioned platforms: a model constructed using a popular top-down approach, and one created by a novel bottom-up approach. Both models use the completed decommissioning projects in the UKCS area as research and verification resources. According to the results, although the cost assessment model constructed using the bottom-up method is challenging, it has higher accuracy and more robust versatility. The top-down approach model is more suitable for governments and energy companies to make rough assessments of the market and projects. The bottom-up approach model is more suitable for a more detailed cost assessment of the decommissioning of individual facilities and can be integrated with results from other assessment models (such as risk and impact assessment models) to obtain more accurate cost assessment results. Both approaches have great room for improvement at present, and further integration of disciplines may be the key to breakthroughs in this field.

Landslide Susceptibility Mapping in Ampang Jaya: Comparing Probabilistic Method and Weighted Overlay Method

When it came time to produce the map, the entire district of Ampang Jaya was chosen as the area for the research. These two approaches gave very different results in terms of accuracy. The results of the map were categorised using a range of different classification techniques, some of which include Natural Breaks and Equal Interval, respectively. Various landslide susceptibility hazard zoning results were found when the two different classification systems were applied to the data. These zoning areas need to go through an accuracy assessment process in order to be validated. The accuracy of the model was evaluated by comparing the findings about the historical locations of landslide occurrences with the findings regarding the susceptibility hazard locations of potential landslide areas. Because the accuracy of the Probabilistic technique was 66.67% for Equal Interval and 73.33% for Natural Breaks, respectively, this demonstrates that the Probabilistic method produces more dependable results than the Weighted Overlay method produces. Therefore, the accuracy assessment results indicate that the probabilistic method provides more reliable information for accuracy assessment than the Weighted Overlay method. This is due to the fact that the result of the accuracy assessment obtained from Weighted Overlay is significantly lower than that obtained from Probabilistic for each classification technique.

MADM-Q, an efficient multi-attribute decision-making support system for offshore decommissioning

With decades of development, some offshore facilities are reaching their design lives and need to be decommissioned. However, due to the limitation of regulations, technologies, and other aspects, which decommissioning options should be chosen is a challenging task. This paper introduces a multi-attribute quantitative evaluation system called MADM-Q (Multi-Attribute Decision Making-Quantitative), which can show decision makers with decommissioning options’ cost, risk, and environmental impact assessment results. The system consists of an input, output, and three processing modules. The Engineering Cost Evaluation System (ECES) is the first bottom-up approach cost assessment model in offshore facility decommissioning research. The Hierarchical Analyst Domino Evaluation System (HADES) acts as the risk assessment module, considering Domino Effect Accidents (DEAs) and providing accurate and rapid quantitative risk assessment results. The third sub-model, Composite Impact Evaluation System (CIES) assesses the environmental and socioeconomic impacts of the project. The system can obtain the basic cost range and the Individual Risk Per Annum (IRPA) value of the project quickly by using some simple inputs. The results of ECES and HADES reflects excellent accuracy - 12% cost evaluation average deviation and 1.43E-04 IRPA evaluation bias. Although currently, the HADES is a quasi-dynamic risk assessment method, it would be easy to develop it into a real-time dynamic risk monitoring and assessment system by combining advanced technologies such as digital twin technology and sensor technology.

Data Mining of Formative and Summative Assessments for Improving Teaching Materials towards Adaptive Learning: A Case Study of Programming Courses at the University Level

It is crucial to review and update course materials regularly in higher education. However, in the course evaluation process, it is debatable what a difficult learning topic is. This paper proposes a data mining approach to detect learning topics requiring attention in the improvement process of teaching materials by analyzing the discrepancy between formative and summative assessments. In addition, we propose specific methods involving clustering and noise reduction using the OPTICS algorithm and discrepancy calculation steps. Intensive experiments have been conducted on a dataset collected from accurate assessment results of the data structures and algorithms (DSA) course for IT major students at our university. The experimental results have shown that noise reduction can assist in identifying underperforming and overperforming students. In addition, our proposed method can detect learning topics with a high discrepancy for continuously improving teaching materials, which is essential for question recommendation in adaptive learning systems.