Expert Observers Research Articles

Generation of Programmatic Contents by Competencies: A Technological and Systemic View of Higher Education

This research combines the art of designing programmatic contents by competencies and the technological variable as an innovative resource in the context of higher education. The objective of this study was focused on the development of a technological system for the generation of programmatic contents by competencies in the curricular units of university careers. This research was carried out under the empirical approach; it is of an applicative type, since it generates a proposal and it was structured methodologically by phases: Phase I of approaching the manual system and user requirements was deployed under a field design in which the current situation and user expectations were described through the techniques of participant observation and meetings of experts in the area of educational technology (teaching staff of the different academic programs, heads of departments and coordinators of the Curriculum Commission), in order to carry out business rounds as a strategy of characterization and permanent consultation of the evolution of the system design to generate agreements. Phase II led to the establishment of the structural components of the prototype, and integrated the essentials from the systems theory, software engineering, and pedagogical didactic theories. Phase III was based on the methodology of system design by prototyping. As for the results, it was evidenced that the stakeholders considered feasible the use of the system to generate programmatic contents by competence, and finally the functionality of the system and the operational advantages for the generation of programmatic contents were demonstrated.

Interactions of Functional Traits With Native Status and Ecosystem Novelty Explain the Establishment of Plant Species Within Urban Ecosystems: Evidence From Berlin, Germany

A key challenge in urban biodiversity conservation is to understand the drivers that govern the population establishment of different groups of species in different urban ecosystems. Here, we ask whether and to what extent vascular plant species establishment (i.e., the ability to establish self-sustaining populations within a certain time span) is driven by interactions of species functional traits, native status, and the type of ecosystem species occur in, with types of ecosystems distinguished by their degree of ecosystem novelty. To answer this question, we use a dataset of 1,178 vascular plant species occurring in Berlin, Germany that originally had been compiled to substantiate the Berlin Red List of endangered plant species. This dataset classifies native and non-native species into casual and established species based on a minimum of 25 years of expert observation. Whether a species is established or casual is distinguished among four broad types of ecosystems: natural remnant, hybrid, novel immature, and novel mature ecosystems. Moreover, we classify species into those native to Berlin and non-native species (split into archaeophytes and neophytes), and link species to selected functional traits and indicator values. By applying ordinal regression within a Bayesian framework, we show that traits are key drivers of these establishment processes and that the traits that drive species establishment differ across types of ecosystems. While across traits, more established species are present in natural remnants, low canopy height, annual life span, and late end of flowering specifically promote establishment in novel immature ecosystems. In hybrid ecosystems, low canopy height and reproduction by seeds are beneficial traits, with the latter promoting establishment in novel mature ecosystems, too. Traits were less important in predicting species establishment in native as compared to non-native species. All types of ecosystems add to urban biodiversity, and trait analyses refine our knowledge on how they can be supported in doing so on the long term. This can help in sharpening conservation measures.

Phenomic data-facilitated rust and senescence prediction in maize using machine learning algorithms

Current methods in measuring maize (Zea mays L.) southern rust (Puccinia polyspora Underw.) and subsequent crop senescence require expert observation and are resource-intensive and prone to subjectivity. In this study, unoccupied aerial system (UAS) field-based high-throughput phenotyping (HTP) was employed to collect high-resolution aerial imagery of elite maize hybrids planted in the 2020 and 2021 growing seasons, with 13 UAS flights obtained from 2020 and 17 from 2021. In total, 36 vegetation indices (VIs) were extracted from mosaicked aerial images that served as temporal phenomic predictors for southern rust scored in the field and senescence as scored using UAS-acquired mosaic images. Temporal best linear unbiased predictors (TBLUPs) were calculated using a nested model that treated hybrid performance as nested within flights in terms of rust and senescence. All eight machine learning regressions tested (ridge, lasso, elastic net, random forest, support vector machine with radial and linear kernels, partial least squares, and k-nearest neighbors) outperformed a general linear model with both higher prediction accuracies (92–98%) and lower root mean squared error (RMSE) for rust and senescence scores (linear model RMSE ranged from 65.8 to 2396.5 across all traits, machine learning regressions RMSE ranged from 0.3 to 17.0). UAS-acquired VIs enabled the discovery of novel early quantitative phenotypic indicators of maize senescence and southern rust before being detectable by expert annotation and revealed positive correlations between grain filling time and yield (0.22 and 0.44 in 2020 and 2021), with practical implications for precision agricultural practices.

Extended Intraoperative Longitudinal 3-Dimensional Cone Beam Computed Tomography Imaging With a Continuous Multi-Turn Reverse Helical Scan.

Cone beam computed tomography (CBCT) imaging is becoming an indispensable intraoperative tool; however, the current field of view prevents visualization of long anatomical sites, limiting clinical utility. Here, we demonstrate the longitudinal extension of the intraoperative CBCT field of view using a multi-turn reverse helical scan and assess potential clinical utility in interventional procedures. A fixed-room robotic CBCT imaging system, with additional real-time control, was used to implement a multi-turn reverse helical scan. The scan consists of C-arm rotation, through a series of clockwise and anticlockwise rotations, combined with simultaneous programmed table translation. The motion properties and geometric accuracy of the multi-turn reverse helical imaging trajectory were examined using a simple geometric phantom. To assess potential clinical utility, a pedicle screw posterior fixation procedure in the thoracic spine from T1 to T12 was performed on an ovine cadaver. The multi-turn reverse helical scan was used to provide postoperative assessment of the screw insertion via cortical breach grading and mean screw angle error measurements (axial and sagittal) from 2 observers. For all screw angle measurements, the intraclass correlation coefficient was calculated to determine observer reliability. The multi-turn reverse helical scans took 100 seconds to complete and increased the longitudinal coverage by 370% from 17 cm to 80 cm. Geometric accuracy was examined by comparing the measured to actual dimensions (0.2 ± 0.1 mm) and angles (0.2 ± 0.1 degrees) of a simple geometric phantom, indicating that the multi-turn reverse helical scan provided submillimeter and degree accuracy with no distortion. During the pedicle screw procedure in an ovine cadaver, the multi-turn reverse helical scan identified 4 cortical breaches, confirmed via the postoperative CT scan. Directly comparing the screw insertion angles (n = 22) measured in the postoperative multi-turn reverse helical and CT scans revealed an average difference of 3.3 ± 2.6 degrees in axial angle and 1.9 ± 1.5 degrees in the sagittal angle from 2 expert observers. The intraclass correlation coefficient was above 0.900 for all measurements (axial and sagittal) across all scan types (conventional CT, multi-turn reverse helical, and conventional CBCT), indicating excellent reliability between observers. Extended longitudinal field-of-view intraoperative 3-dimensional imaging with a multi-turn reverse helical scan is feasible on a clinical robotic CBCT imaging system, enabling long anatomical sites to be visualized in a single image, including in the presence of metal hardware.

System for Central Venous Catheterization Training Using Computer Vision-Based Workflow Feedback.

To develop a system for training central venous catheterization that does not require an expert observer. We propose a training system that uses video-based workflow recognition and electromagnetic tracking to provide trainees with real-time instruction and feedback. The system provides trainees with prompts about upcoming tasks and visual cues about workflow errors. Most tasks are recognized from a webcam video using a combination of a convolutional neural network and a recurrent neural network. We evaluated the system's ability to recognize tasks in the workflow by computing the percent of tasks that were recognized and the average signed transitional delay between the system and reviewers. We also evaluated the usability of the system using a participant questionnaire. The system was able to recognize 86.2% of tasks in the workflow. The average signed transitional delay was -0.7s. The average usability score on the questionnaire was 4.7 out of 5 for the system overall. The participants found the interactive task list to be the most useful component of the system with an average score of 4.8 out of 5. Overall, the participants' response to the system was positive. Participants perceived that the system would be useful for central venous catheterization training. Our system provides trainees with meaningful instruction and feedback without needing an expert observer to be present. We are able to provide trainees with more opportunities to access instruction and meaningful feedback by using workflow recognition.

Training Students' Science Literacy on Biotechnology Using Science, Environmental, Technology, Society (SETS) Visioned Learning Instructional

The aim of this research is to develop science learning instructional based on Science Environment Society Technology (SETS) approach which is faceable to facilitate students science literacy. Science learning instructional that developed in this research are lesson plans, student teaching materials, students worksheets and scientific literacy instruments. The method used in this study is the research and development (RnD) using the Dick and Carey model and it was tested to ninth grade students of SMP Negeri 4 Langke Rembong on second semester of 2021/2022 Academic Year. Data were collected using expert validation, observation and test methods. Data were analyzed descriptively quantitative and qualitative. The results of the research show that 1) the science learning instructional developed was valid after being validated by two science teachers and two science lecturers, 2) the practicality of the learning device was obtained from the implementation of the lesson plan in the very good category, 3) the effectiveness of the device was demonstrated by increasing scores and levels scientific literacy with moderate n-gain and student responses to devices and learning implementation are interesting and easy to learn. Based on these results, it can be concluded that science learning instructional based on SETS approach are suitable for practicing student scientific literacy

Diagnostic accuracy of code-free deep learning for detection and evaluation of posterior capsule opacification

ObjectiveTo train and validate a code-free deep learning system (CFDLS) on classifying high-resolution digital retroillumination images of posterior capsule opacification (PCO) and to discriminate between clinically significant and non-significant PCOs.Methods...

Development of e-module based on local wisdom to improve science literacy and reading literacy

This research is motivated by (1) the results of reading literacy and science literacy in PISA, which is still low, and (2) technology and cultural-based learning media have not been developed by private high school chemistry teachers in Semarang. This research aims to develop a feasible E-module based on the local wisdom of spice drinks that can improve reading literacy and learners' science literacy. This research is a research and development with a 3-D model, which includes defining, designing, and developing. This study collects data through observation, questionnaires, and testing. The research instruments used are material expert validation sheets, multimedia expert validation, observation sheets, and instruments about reasoned multiple choice. The study subject was eight students of XI MIPA Kebon Dalem high school. Expert validation results of the material showed 92.85% (very valid). The validation results of media experts showed 85.71% (valid). E-modules are declared effective because there is an increase in the completion of learners' learning outcomes after using E-modules. E-Module based on local wisdom of spice drinks can visualize the factors that affect the rate of reaction material. So, it can be concluded that E-modules based on local wisdom spice drinks developed are worth using to improve learners' reading and science literacy.

Objective Comparison of Achievement Motivation and Competitiveness among Semi-Professional Male and Female Football Players

The aim of this study was to examine differences in achievement motivation (measured with the Objective Achievement Motivation Test, OLMT, Schuhfried®) and competitiveness between male and female semi-professional football players. The OLMT objectively assessed three constructs regarding achievement motivation: motivation through personal goals, aspiration level, and motivation through competition. In addition, competitiveness was measured with the self-reported Competitiveness-10 Questionnaire. Finally, participants’ performance was assessed by three expert observers in each of ten matches. Thirty-eight football players (men = 27; women = 11) participated in the present study, and no significant differences were found in the Levene test when comparing men and women with respect to the scores obtained in the different measures used in our research. Significant differences were found in the motivation through competition (p = 0.021) as well as in self-reported competitiveness (p = 0.020) as a function of gender, with males showing higher values in both cases. No gender differences were found in aspiration level (p = 0.283) or motivation through personal goals (p = 0.897). Moreover, age and player performance did not modulate gender differences on any measures. No significant correlation was found between motivational measures and performance. In conclusion, it should be noted that the only variable on which gender differences emerged was the level of competitiveness, such that males scored higher than females on both objective and self-reported measures.

Inter-observer and intra-observer agreement in drug-induced sedation endoscopy \u2014 a systematic approach

ObjectiveTo evaluate the feasibility of systematic observer training in drug-induced sedation endoscopy (DISE) interpretation.MethodsFifty DISE videos were randomly selected from a group of 200 videos of cohort of patients with OSA and/or snoring. The videos were assessed blindly and independently using a modified VOTE classification by an expert observer and by two novice observers starting their training. A systematic approach was initiated. Clusters of 10 videos were scored individually by each observer and then re-evaluated as the expert observer clarified the decision-making in plenum. Kappa coefficient (κ) was calculated as a measure of agreement.ResultsThe intra-observer variation for the total agreement and kappa values for the expert observer ranged between moderate to substantial agreement in VOTE classification, whereas the novices varied between “less than chance agreement” to “moderate agreement.” The inter-observer variation showed increased agreement and kappa values from day 1 to day 2 for both novice observers except at the velum level for observer C. The total agreement and kappa values for each site also improved compared to results of day 1, except at velum for observer C. The velum site seemed to be more difficult to evaluate. The learning curve varied during the study course for each site of the upper airways.ConclusionThis study shows that systematic intensive training is feasible, although expert level is not acquired after 100 evaluations. The learning curve for the expert observer showed “moderate to substantial agreement” but differed between the trainees.Level of evidence2

Social reputation influences on liking and willingness-to-pay for artworks: A multimethod design investigating choice behavior along with physiological measures and motivational factors.

Art, as a prestigious cultural commodity, concerns aesthetic and monetary values, personal tastes, and social reputation in various social contexts-all of which are reflected in choices concerning our liking, or in other contexts, our actual willingness-to-pay for artworks. But, how do these different aspects interact in regard to the concept of social reputation and our private versus social selves, which appear to be essentially intervening, and potentially conflicting, factors driving choice? In our study, we investigated liking and willingness-to-pay choices using-in art research-a novel, forced-choice paradigm. Participants (N = 123) made choices from artwork-triplets presented with opposing artistic quality and monetary value-labeling, thereby creating ambiguous choice situations. Choices were made in either private or in social/public contexts, in which participants were made to believe that either art-pricing or art-making experts were watching their selections. A multi-method design with eye-tracking, neuroendocrinology (testosterone, cortisol), and motivational factors complemented the behavioral choice analysis. Results showed that artworks, of which participants were told were of high artistic value were more often liked and those of high monetary-value received more willingness-to-pay choices. However, while willingness-to-pay was significantly affected by the presumed observation of art-pricing experts, liking selections did not differ between private/public contexts. Liking choices, compared to willingness-to-pay, were also better predicted by eye movement patterns. Whereas, hormone levels had a stronger relation with monetary aspects (willingness-to-pay/ art-pricing expert). This was further confirmed by motivational factors representative for reputation seeking behavior. Our study points to an unexplored terrain highlighting the linkage of social reputation mechanisms and its impact on choice behavior with a ubiquitous commodity, art.

To the problem of death of children from closure of respiratory tract by foreign object: expert observation

In the special forensic literature, information on the deaths of children from mechanical asphyxiation as a result of closure of the airways by foreign objects is small and fragmentary, a small number of works are devoted to them, despite the fact that the social significance of this problem is great.
 An expert observation of a case of asphyxia developed in a child as a result of closure of the upper respiratory tract by a foreign object is given. The child played for 1.5 years and suddenly began to choke. A forensic examination of the corpse revealed the presence of a foreign body (part of a childs toy) in the area of the vocal cords, completely covering the lumen of the entrance to the larynx; acute pulmonary bloating, hemorrhages in soft tissues from the area of entrance to the larynx, foci of acute pulmonary alveoli emphysema, hemorrhages in pulmonary tissue, signs of rapid death.
 Forensic medical diagnosis: mechanical asphyxia from closing the lumen of the respiratory tract with a foreign body (the presence of a foreign body in the vocal cords, completely blocking the lumen of the entrance to the larynx; acute swelling of the lungs, hemorrhages in the soft tissues from the entrance to the larynx, foci of acute emphysema of the pulmonary alveoli, hemorrhages in the lung tissue, signs of rapid death).
 The work of a forensic medical expert is often hampered by the lack of clinical data and the circumstances of the incident, as well as difficulties in interpreting the results of the study. In cases where adults are present during the aspiration of a foreign body by a child, respiratory failure is recorded with cyanosis of the face, breath holding, followed by paroxysmal unproductive cough, which indicates an existing threat of asphyxia. In this expert observation, the detailed circumstances of the incident provided by law enforcement agencies and the asphyxic alertness of the expert helped to establish the cause of death and formulate a forensic diagnosis and conclusions. However, it is important to understand that cases of death of children from obstructive asphyxia are potentially preventable and require targeted preventive work.

Oral Cavity Anatomical Site Image Classification and Analysis.

Oral cavity cancer is a common cancer that can result in breathing, swallowing, drinking, eating problems as well as speech impairment, and there is high mortality for the advanced stage. Its diagnosis is confirmed through histopathology. It is of critical importance to determine the need for biopsy and identify the correct location. Deep learning has demonstrated great promise/success in several image-based medical screening/diagnostic applications. However, automated visual evaluation of oral cavity lesions has received limited attention in the literature. Since the disease can occur in different parts of the oral cavity, a first step is to identify the images of different anatomical sites. We automatically generate labels for six sites which will help in lesion detection in a subsequent analytical module. We apply a recently proposed network called ResNeSt that incorporates channel-wise attention with multi-path representation and demonstrate high performance on the test set. The average F1-score for all classes and accuracy are both 0.96. Moreover, we provide a detailed discussion on class activation maps obtained from both correct and incorrect predictions to analyze algorithm behavior. The highlighted regions in the class activation maps generally correlate considerably well with the region of interest perceived and expected by expert human observers. The insights and knowledge gained from the analysis are helpful in not only algorithm improvement, but also aiding the development of the other key components in the process of computer assisted oral cancer screening.

Histopathological study of round cell tumors of the head and neck region in a tertiary care hospital: A retrospective study

Background: Small round cell tumors are heterogeneous, highly aggressive malignant tumors occuring in unusual sites with overlapping clinical and radiographic features. Their diagnosis is challenging using conventional histopathologic approaches because of indistinct features in small biopsy samples and hence immunohistochemistry is a must. This study was undertaken to evaluate the pattern, common types, age, sex distribution of round cell tumors of the head and neck region and to obtain morphological immunohistochemistry correlation. Material and Methods: It is a retrospective study of 99 cases which fulfilled the inclusion criteria. Paraffin blocks were retrieved and were reviewed by two independent expert observers and immunohistochemistry was repeated whenever necessary. Results: Final diagnosis was given based on the immunohistochemistry pattern and our study showed 8 spectrums of round cell tumours. Lymphoma was the most common followed by neuroendocrine carcinoma. Most B-cell Non Hodgkin Lymphoma, undifferentiated carcinomas and Neuroendocrine carcinomas were observed in older group whereas, Ewing sarcoma /Primitive Neuro Ectodermal Tumour and T cell NHL were seen more in younger group. According to sex wise distribution, 70 (70.7%) cases were male and 29 (29.3%) females with male to female ratio of 2.4:1. Conclusions: Round cell tumors can occur at any sites of the head and neck region. There are certain morphologic features for each tumor which may help the surgical pathologist to come to a probable diagnosis in addition to careful search of the detailed history, location of tumor, presentation, radiological findings and ultimately correlating with immunohistochemistry.

Revealing the Competence of Multiprofessional Team Building among Students and Its Impact on the Effectiveness of Team Interaction

Introduction. The need for a multiprofessional team is critical for the preschool stage where problems of individualization of education for children with disabilities and gifted children with behavioral deviations are solved. Despite the large number of publications on multiprofessional education, there are almost no researches into the readiness to multiprofessional interaction of preschool education specialists. The aim of the article is to present the results and methods for revealing the level of multiprofessional team building competence of students – future preschool education workers, to analyze the differences between the groups with high level of multiprofessional team building competence and the groups with low effectiveness of team interaction. Materials and Methods. Research sample: students of Shadrinsk State Pedagogical University (Russia) and Kazakh National Womenʼs Pedagogical University (Kazakhstan). Methods: expert observation (teachers competent in the fields of knowledge that students should operate in the research process were involved) using “field notes” and video recordings (qualitative and quantitative assessment according to the methodology of V.I. Zagvyazinsky, R. Atakhanov); questionnaires; interviews in focus groups; testing; expert evaluation of the effectiveness of team interaction; statistical criteria: Kolmogorova-Smirnova (single-sample) to determine the normality of distribution; Mann-Whitney U-criterion to identify the reliability of differences in groups with high levels of formation multiprofessional competencies from groups with low efficiency of team interaction. Results. It is proved that the formation of competence of multiprofessional team building is significant for the effectiveness of team interaction. The problems of multiprofessional interaction of preschool education workers are revealed: lack of willingness to conduct a dialogue with each other, weak or low degree of team-building and co-organizing activity, an attempt to associate the problem with the activity of one specialist, the desire to find the culprit in the situation. Discussion and Conclusion. The obtained results contribute to the development of the issue of readiness for interaction of specialists in defectological and non-defectological areas of training. In the future, it is advisable to investigate the issues of designing and evaluating the effectiveness of courses that develop the competencies of multiprofessional team building. The materials of the article can be useful in the developing standards of higher education of a new generation in terms of designing the planned learning outcomes of the academic programs and international recommendations on education.

Auto-Segmentation of Oropharyngeal Cancer Primary Tumors Using Multiparametric MRI-Based Deep Learning

<h3>Purpose/Objective(s)</h3> Segmentation of oropharyngeal cancer (OPC) primary gross tumor volumes (GTVp) is crucial for radiotherapy planning. Multiparametric MRI (mpMRI) acquisitions that incorporate anatomical and functional sequences are being increasingly used for OPC-adaptive radiotherapy workflows and will play a prominent role in GTVp segmentation. However, human-generated segmentations are error-prone and suffer from high inter-observer variability. Therefore, we constructed mpMRI deep learning OPC GTVp auto-segmentation models and determined the impact of variable mpMRI channels on segmentation performance. <h3>Materials/Methods</h3> GTVp ground truth segmentations were manually generated for 30 OPC patients on T2-weighted (T2) MRI from a prospective clinical trial. We evaluated 5 mpMRI input channels (T2, T1-weighted [T1], apparent diffusion coefficient [ADC], volume transfer constant [Ktrans], and fractional volume [Ve]). 3D Residual U-net models for different channel combinations were developed and assessed using a leave-one-out cross-validation approach. A baseline T2 model was compared to mpMRI models (T2+T1, T2+ADC, T2+Ktrans, T2+Ve, all five channels [ALL]) primarily using the Dice similarity coefficient (DSC). Sensitivity, positive predictive value, Hausdorff distance (HD), false-negative DSC (FND), false-positive DSC, surface DSC, 95% HD, and mean surface distance were also assessed. For the best model, ground truth and model-generated segmentations were compared through a Turing test using three physician observers. <h3>Results</h3> Our models demonstrated high performance across all evaluation metrics, with mean DSCs of 0.71 (ALL) to 0.73 (T2+T1). Compared to the baseline T2 model, performance was significantly improved for HD, FND, sensitivity, Surface DSC, and 95% HD for the T2+T1 model (p<0.05) and for FND for the T2+Ve and ALL models (p<0.05). No model demonstrated significant correlations between tumor size and DSC (p>0.05). Most models demonstrated significant correlations between tumor size and HD or Surface DSC (p<0.05), with the exception of those that included ADC or Ve as input channels (p>0.05). The Turing test revealed no significant difference between the best performing model (T2+T1) and the ground truth segmentations for all expert observers (p>0.05). <h3>Conclusion</h3> Deep learning using mpMRI data provides high-quality segmentations of OPC GTVp, where clinical experts are unable to determine any meaningful differences between ground truth and model segmentations. The incorporation of additional mpMRI channels may increase the performance of certain evaluation metrics and improve model robustness and consistency. This pilot study is a promising step towards future large-scale studies for fully automated MR-guided OPC radiotherapy.

70 Evaluating Network Maps from Student Self-reflections During a Departmental Internship Program

Abstract Student reflection presents opportunities to think through the learning process especially in a non-guided experiential learning course where students themselves need to focus on learning outcomes and course objectives. The purpose of this study is to explore students learning experiences by examining their reflections of university students participating in internships in the animal science industry during the summer semester of 2021 while taking coursework at the university. A total of 12 bi-weekly reflections collected and a qualitative thematic analysis was conducted with strengths, struggles, skill development, and disposition development as major theme categories. The reflections were coded in MAXQDA and network maps were created with Girvan-Newman cluster analyses in the UCINET and NetDraw software. We identified 5 clusters (Q=0.613) from correlations of the reflection codes at P &amp;lt; 0.01 (Fig.1). In the cluster with the highest correlations, students associated internship activities with networking opportunities, gaining new perspectives, observation of experts working in context, and problem-solving, indicating that most students appreciated these aspects of the program. In another cluster, students associated skill development, experiential learning opportunities, and collaborations, with productive failure indicating that they learn from trying and making mistakes. In the third cluster, students' perceptions of career advancement, mental stamina, and work ethic were correlated with reduced confidence in their new work environment. In the fourth cluster, students identify that the activity stimulated curiosity, however, this is linked with necessary repetition, collaboration, and interpersonal skills while they struggle with the application of the concepts in the real world. In the final cluster, students’ career experience was correlated with their development of marketing skills, sense of self, responsibility, and time management. Although the internship program enhanced the students' knowledge and skills, a structured instead of open reflection is recommended to gain a better understanding of the overall picture.

The Use of Audio-Visual Media in Improving Students' Reading Comprehension and Sholat Movements in Online Learning

In the Covid-19 pandemic situation, learning that requires practice and habituation patterns such as prayer is experiencing obstacles. Teachers and parents also have problems finding the right learning media so that children's prayer understanding is better. Preliminary study obtained data on the ability of elementary school children in Class I is still far from the Minimum Completeness Criteria (KKM) when online learning is implemented since the child enters school. This research used classroom action research, which aims to describe 1)how to apply prayer audio visual media, and 2) how is the student's understanding of prayer which includes aspects of the ability to recite prayer readings and pray according to the sequence of prayer movements. The research subjects were 18 students of class I, with the researcher as a class teacher and the principal as an expert observer and assessor. Methods of data collection using observation and interview. The instrument consists of media assessment by experts, teacher observation instruments and student abilities. The data analysis used is narrative-qualitative, which describes the findings obtained in the implementation of the action in the form of diagrams and tables. The results of the action after using audio-visual media, students' understanding experienced an increase in prayer readings from 11% which was good to 95% good, and movement ability from 6% to 94%. The conclusion is that the use of audio-visual media in online learning can improve students' understanding of prayer on the ability to read and perform movements in accordance with the guidance of the Prophet SAW.

The Role of the Archeological Heritage Sites in the Process of Urban Regeneration of UNESCO’s Cities—Boka Bay Case Study

The role of the archeological and cultural heritage sites in the process of urban regeneration in UNESCO’s protected areas becomes more and more important for the natural and cultural heritage protection in the touristic cities with urban expansion. However, there is no clear methodological approach for the inclusion of these important natural and cultural heritage sites in the process of urban regeneration of the cities. The purpose of this study is to analyze how two contemporary urban planning tools, sustainable urban mobility plans and heritage impact assessments, contribute to the protection and sustainable use of archeological sites. The methodology that is used in this study is dual, theoretical, through literature review, and empirical, through the appliance of the case study method and expert observation and mapping of the most valuable archeological sites in Boka Bay. The results of this study show that practical usage of the two proposed tools in the process of urban regeneration could help in cultural and natural heritage protection and their inclusion as drivers of sustainable urban planning and cultural heritage management. The results of the study confirm the authors’ hypothesis that the role of the archeological sites in the process of urban regeneration is evident in the touristic cities in the coastal area of Montenegro, concluding that urban mobility principles and heritage impact assessment studies must be considered in the process of urban regeneration while at the same time cultural (archeological) heritage management is an integral part of this process.

Machine learning-based automatic sleep apnoea and severity level classification using ECG and SpO2 signals

Sleep apnoea is a potentially serious sleep disorder that is characterised by repetitive episodes of breathing interruptions. Traditionally, sleep apnoea is commonly diagnosed in an attended sleep laboratory setting using polysomnography (PSG). The manual diagnosis of sleep apnoea using PSG is, however complex, and time-consuming, as many physiological variables are usually measured overnight using numerous sensors attached to patients. In PSG sleep laboratories, an expert human observer is required to work overnight, and the diagnosis accuracy is dependent on the physician’s experience. A quantitative and objective method is required to improve the diagnosis efficacy, decrease the complexity and diagnosis time and to ensure a more accurate diagnosis. The purpose of this study was then to develop an automatic sleep apnoea and severity classification using a simultaneously recorded electrocardiograph (ECG) and saturation of oxygen (SpO2) signals based on a machine learning algorithm. Different ECG and SpO2 time domain and frequency domain features were extracted for training different machine learning algorithms. For sleep apnoea classification, an accuracy of 99.1%, specificity of 98.1% and sensitivity of 100% were achieved using a support vector machine (SVM) based on combined ECG and SpO2 features. Similarly, for severity classification, an 88.9% accuracy, 90.9% specificity and 85.7% sensitivity have been obtained. For both apnoea and severity classification, using the combined features was found to be more accurate, and this is typically important when either channel is poor quality, the system can make an analysis based on the other channel and achieve good accuracy.