Learning Stage Research Articles

A Novel Deep-Learning-Based QoS Prediction Model for Service Recommendation Utilizing Multi-Stage Multi-Scale Feature Fusion With Individual Evaluations

With the rapid development of service computing, the demand for service recommendation is increasing. Quality of Service (QoS) prediction has been one of the key challenges for service recommendation. Existing deep learning-based methods have been proposed for QoS prediction, but further improvement of their neural network structures is still needed to improve the prediction accuracy. This work introduces multi-stage multi-scale feature fusion with individual evaluations to a deep learning model for accurate QoS prediction. In our model, non-negative matrix factorization is used to extract three-scale (i.e., global, local, and individual) features; distance similarity is exploited to find similar users and services; a multi-stage deep neural network is designed to fuse multi-scale features, where individual evaluations are input to each stage to correct QoS features. Finally, our model is compared with often-cited prediction methods, and the experimental results show that it can more accurately predict QoS than its peers. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Accurate QoS prediction is very helpful to recommend the most suitable services to users among many similar services. Affected by the sparsity of historical data, the accuracy of existing QoS prediction methods is often limited. The multi-scale features of users and services can be used to improve prediction accuracy. This work proposes a new QoS prediction method to do so. Specifically, it first extracts global and individual features through non-negative matrix factorization and uses distance similarity to obtain local features. Then, it proposes a new deep neural network that fuses the extracted multi-scale features in each learning stage, thereby improving QoS prediction for services recommendation.

Proposal for a Hypothetical Learning Path Using GeoGebra in Learning Numerical Sequences

A hypothetical learning path is proposed for the teaching-learning of numerical sequences in second grade secondary school students, it is theoretically based in a Duval’s Theory of Semiotic Representation Registers and methodologically based on GeoGebra &amp; Hypothetical Learning Path. It is intended to contribute to this field of mathematics given that there are not many the works in this regard, a fact that motivates the facilitation of better perspectives for students in learning the mathematical object numerical sequences. According to the hypothetical learning trajectory theory, each stage of learning requires a series of preconditions and appropriate instructional approaches so that the individual can progress. These stages include: 1) Acquisition of basic knowledge 2) Application of skills 3) Automation 4) Integration. It is concluded that it must be applied in the classroom to know the effectiveness of this trajectory.

Internalization of Sundanese Local Wisdom in Strengthening the Profile of Pancasila Students through the Literacy Movement in Madrasah

This study aims to find out and describe the values ​​of Sundanese local wisdom that can be implemented in literacy-based learning in madrasas in the process of strengthening the Pancasila student profile. This study uses a qualitative descriptive method by analyzing the problem and then breaking it down into ideas. the preparation of this paper uses secondary data by reviewing relevant literature from scientific articles. After the data is collected, the analysis is carried out using descriptive and comparative analysis. The profile of Pancasila students is interpreted as a profile of lifelong students with the character of faith and piety to God Almighty, noble character, global diversity, cooperation, independence, critical thinking, and creative reasoning. In this regard, Sundanese local wisdom can be internalized as silih asih, silih asah, silih asuh, silih wawangi, cageur, bageur, bener, pinter and singer. These values ​​are moral values ​​that are firmly held by the Sundanese people and are relevant to strengthening the profile of Pancasila students. In its implementation, these values ​​are designed through the literacy movement by dividing its activities into 3 stages. The first stage is the habituation stage. At this stage, the inculcation of local wisdom values ​​can be divided into each day of the learning process, so in one week of learning, students can form the expected characteristics of the Pancasila student profile. In the second stage, namely the development stage through the literacy corner. The last stage is the learning stage applying learning models that focus on students.

Identification of congenital valvular murmurs in young patients using deep learning-based attention transformers and phonocardiograms.

One in every four newborns suffers from congenital heart disease (CHD) that causes defects in the heart structure. The current gold-standard assessment technique, echocardiography, causes delays in the diagnosis owing to the need for experts who vary markedly in their ability to detect and interpret pathological patterns. Moreover, echo is still causing cost difficulties for low-and middle-income countries. Here, we developed a deep learning based attention transformer model to automate the detection of heart murmurs caused by CHD at an early stage of life using cost-effective and widely available phonocardiography (PCG). PCG recordings were obtained from 942 young patients at four major auscultation locations, including the aortic valve (AV), mitral valve (MV), pulmonary valve (PV), and tricuspid valve (TV), and they were annotated by experts as absent, present, or unknown murmurs. A transformation to wavelet features was performed to reduce the dimensionality before the deep learning stage for inferring the medical condition. The performance was validated through 10-fold cross-validation and yielded an average accuracy and sensitivity of 90.23% and 72.41%, respectively. The accuracy of discriminating between murmurs' absence and presence reached 76.10% when evaluated on unseen data. The model had accuracies of 70%, 88%, and 86% in predicting murmur presence in infants, children, and adolescents, respectively. The interpretation of the model revealed proper discrimination between the learned attributes, and AV channel was found important (score > 0.75) for the murmur absence predictions while MV and TV were more important for murmur presence predictions. The findings potentiate deep learning as a powerful front-line tool for inferring CHD status in PCG recordings leveraging early detection of heart anomalies in young people. It is suggested as a tool that can be used independently from high-cost machinery or expert assessment. With additional validation on external datasets, more insights on the generalizability of deep learning tools could be obtained before being implemented in real-world clinical settings.

Internalization of Character Education Values in Arabic Language Learning for Tsanawiyah Students Dayah Al Muslimun Lhoksukon North Aceh

This study aims to describe the implementation of character education values and their internalization in Arabic language learning for tsnawiyah students of Dayah Al Muslimun Lhoksukon North Aceh. This research uses descriptive qualitative methods, and the data collected are the results of observations, interviews and documentation. Data analysis in this study used Miles Huberman's interactive analysis theory. The data analysis technique in this study begins with collecting data, presenting, reducing and concluding. The results of this study indicate that the value of character education values contained in Arabic learning materials in the book Arabiyah Baina Yadaik for Tsanawiyah students, namely: religious values, ethical values, tolerance values, disciplinary values, complex work values, independent values, democratic values, curiosity values, national spirit values, recognizing excellence, communicative values, reading values, environmental care values and responsibility values and the value of character education values are internalized into the process of Arabic learning stages through teaching materials, learning models and evaluation (authentic assessment).

Esej jako metoda kształcenia studentów – przyszłych nauczycieli geografii

An essay is one of the written forms of expression commonly used in literature. It can also be a method for correctly and ingenious formulation of written statements by pupils and students in the process of their education at various stages of learning and studying. The aim of the article is to present the features and values of the essay as a method used in the process of educating geography students – developing various language skills, including: freedom of expression of one’s own views, subjective assessment of facts and events, and creative involvement – i.e. competences useful to geographers, especially candidates for work in as teachers. The article also includes the results of a survey conducted on the subject of the essay among students of geography teaching specialization or teaching unit / module at five Polish universities, as well as considerations on the advisability of using it as a form of passing a course.

Cultivating Cultural Awareness in Early Childhood: The Role of Batik Tulis in Preserving Local Heritage

This study explores the efficacy of batik tulis (written) for introducing and preserving local cultural heritage in early childhood education. Conducted at TK Batik PPBI Yogyakarta, this qualitative research utilized observations, interviews, and documentation to assess how batik-making activities influence cultural awareness among preschoolers. Results reveal that the batik introduction process familiarizes children with this local art form and instills a profound appreciation for cultural traditions. The educational methodology was designed to be age-appropriate and interactive, integrating safety measures and encouraging active participation throughout all stages of learning—from understanding the cultural significance of batik to hands-on crafting. The findings highlight the pivotal role of integrating cultural elements into early education to cultivate a long-lasting appreciation and knowledge of local heritage. This approach not only aids in cultural preservation but also enriches the educational experience, fostering a generation that values and understands its cultural roots. However, the study's limited scope, focused on a single educational setting, suggests the need for further research. Future studies should aim to replicate and validate these findings across various educational contexts to understand better the effectiveness and scalability of integrating cultural education in early childhood settings. These insights advocate for educational reforms recognizing and utilizing local cultural heritage as a fundamental component of comprehensive educational strategies, potentially influencing broader pedagogical practices.

Challenges Faced by Beginner Instructors and their Influence on Job Performance at University Level

This study deals with the challenges of novice teachers and their impact on professional performance. Moreover, novice instructors are those who are starting their careers and are in the learning stage. Furthermore, they have less than five years of experience and they face both internal and external challenges that have an impact on job performance. The population of the study comprises all novice teachers of the Islamia University of Bahawalpur. The sample of the study consisted of 210 novice teachers randomly selected from the population. Data was collected through a questionnaire and collected data was organized and interpreted as mean score, frequency score, and percentage. The main recommendation of the study was the supportive behavior of senior teachers and an encouraging job environment helpful in novice teachers' job performance.

ANALISIS NILAI-NILAI KARAKTER SISWA DALAM PEMBELAJARAN PPKn DI KELAS VII SMP SWASTA FAJAR MAS LASORI II

The aims of this research are 1) To find out what the character values ​​of students are in learning in class VII of Fajar Mas Lasori II Private Middle School and 2) To find out Civics learning in class VII of Fajar Mas Lasori II Private Middle School. This type of research is qualitative research using a descriptive approach. The subjects in this research were PPKn subject teachers and class VII students at Fajar Mas Lasori II Private Middle School. Data collection techniques in this research used 1) Observation Techniques, 2) Interview Techniques, 3) Documentation Techniques. The data analysis technique in this research uses 1) Data Reduction, 2) Data Presentation, 3) Conclusion Drawing. The results of this research indicate that the character values ​​of students in class VII PPKn learning at Fajar Mas Lasori II Private Middle School are good. So it can be concluded that 1) Based on the results of interviews with teachers and students presented in Chapter VI, it can be concluded that the character values ​​of class VII students at Fajar Mas Lasori II Private Middle School are good 2) The results of this research data analysis show that PPKn learning in class VII Fajar Mas Lasori II Private Middle School has been integrated with all character values. Suggestions from researchers 1) To the school, to achieve ideal student character values, it is best to implement, supervise the process, and evaluate student character values ​​in accordance with predetermined standards, not only during the PPKn learning process but at all stages of learning at school and outside school. 2) Subject teachers must continue to develop educational skills to master various methods, strategies and techniques in the learning process to achieve the predetermined character achievement indicators.

Impact of scaffolding and hands-on assignments within mechatronics on student learning outcomes of KEEN's entrepreneurial mindset

Scaffolding learning and incorporating hands-on activities are proven pedagogical techniques that improve student engagement. A growing movement within engineering education has been to educate beyond the technical skills and foster an improvement in students’ entrepreneurial mindset. A modified version of a validated self-efficacy tool is used here to assess the impact that scaffolding and hands-on activities within a Mechatronics course have on developing the three student learning outcomes associated with the Kern Entrepreneurial Engineering Network's entrepreneurial mindset: “curiosity,” “connections,” and “creating value” (3Cs). A total of 229 students were considered in this study. Presurveys and postsurveys were used to collect self-efficacy ratings for confidence, success, motivation, and anxiety with respect to each of the 3Cs. Additionally, for comparisons a baseline behavioral tool was assessed along with students self-reported prior experiences relevant to the course and overall time spent on course activities. The group was split into high-performers and low-performers for the purpose of analysis. For all 3Cs, aspects of student perceived confidence and success significantly increased between the presurveys and postsurveys for the entire group. However, student perceived motivation was not significantly improved for any of the 3Cs. Interestingly for “connections,” student perceived anxiety decreased only for the high-performing group. This study suggests that changes in these 3Cs can be identified within a single course when subaspects of the mindset are considered.

Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning

While decentralized training is attractive in multi-agent reinforcement learning (MARL) for its excellent scalability and robustness, its inherent coordination challenges in collaborative tasks result in numerous interactions for agents to learn good policies. To alleviate this problem, action advising methods make experienced agents share their knowledge about what to do, while less experienced agents strictly follow the received advice. However, this method of sharing and utilizing knowledge may hinder the team's exploration of better states, as agents can be unduly influenced by suboptimal or even adverse advice, especially in the early stages of learning. Inspired by the fact that humans can learn not only from the success but also from the failure of others, this paper proposes a novel knowledge sharing framework called Cautiously-Optimistic kNowledge Sharing (CONS). CONS enables each agent to share both positive and negative knowledge and cautiously assimilate knowledge from others, thereby enhancing the efficiency of early-stage exploration and the agents' robustness to adverse advice. Moreover, considering the continuous improvement of policies, agents value negative knowledge more in the early stages of learning and shift their focus to positive knowledge in the later stages. Our framework can be easily integrated into existing Q-learning based methods without introducing additional training costs. We evaluate CONS in several challenging multi-agent tasks and find it excels in environments where optimal behavioral patterns are difficult to discover, surpassing the baselines in terms of convergence rate and final performance.

Pre-trained Online Contrastive Learning for Insurance Fraud Detection

Medical insurance fraud has always been a crucial challenge in the field of healthcare industry. Existing fraud detection models mostly focus on offline learning scenes. However, fraud patterns are constantly evolving, making it difficult for models trained on past data to detect newly emerging fraud patterns, posing a severe challenge in medical fraud detection. Moreover, current incremental learning models are mostly designed to address catastrophic forgetting, but often exhibit suboptimal performance in fraud detection. To address this challenge, this paper proposes an innovative online learning method for medical insurance fraud detection, named POCL. This method combines contrastive learning pre-training with online updating strategies. In the pre-training stage, we leverage contrastive learning pre-training to learn on historical data, enabling deep feature learning and obtaining rich risk representations. In the online learning stage, we adopt a Temporal Memory Aware Synapses online updating strategy, allowing the model to perform incremental learning and optimization based on continuously emerging new data. This ensures timely adaptation to fraud patterns and reduces forgetting of past knowledge. Our model undergoes extensive experiments and evaluations on real-world insurance fraud datasets. The results demonstrate our model has significant advantages in accuracy compared to the state-of-the-art baseline methods, while also exhibiting lower running time and space consumption. Our sources are released at https://github.com/finint/POCL.

Semi-supervised Open-World Object Detection

Conventional open-world object detection (OWOD) problem setting first distinguishes known and unknown classes and then later incrementally learns the unknown objects when introduced with labels in the subsequent tasks. However, the current OWOD formulation heavily relies on the external human oracle for knowledge input during the incremental learning stages. Such reliance on run-time makes this formulation less realistic in a real-world deployment. To address this, we introduce a more realistic formulation, named semi-supervised open-world detection (SS-OWOD), that reduces the annotation cost by casting the incremental learning stages of OWOD in a semi-supervised manner. We demonstrate that the performance of the state-of-the-art OWOD detector dramatically deteriorates in the proposed SS-OWOD setting. Therefore, we introduce a novel SS-OWOD detector, named SS-OWFormer, that utilizes a feature-alignment scheme to better align the object query representations between the original and augmented images to leverage the large unlabeled and few labeled data. We further introduce a pseudo-labeling scheme for unknown detection that exploits the inherent capability of decoder object queries to capture object-specific information. On the COCO dataset, our SS-OWFormer using only 50% of the labeled data achieves detection performance that is on par with the state-of-the-art (SOTA) OWOD detector using all the 100% of labeled data. Further, our SS-OWFormer achieves an absolute gain of 4.8% in unknown recall over the SOTA OWOD detector. Lastly, we demonstrate the effectiveness of our SS-OWOD problem setting and approach for remote sensing object detection, proposing carefully curated splits and baseline performance evaluations. Our experiments on 4 datasets including MS COCO, PASCAL, Objects365 and DOTA demonstrate the effectiveness of our approach. Our source code, models and splits are available here https://github.com/sahalshajim/SS-OWFormer

Student’s Self-Regulated Learning in Online Class Design Based on Reflective Learning

This study explored the connection between Self-Regulated Learning (SRL) strategies and student learning outcomes, alongside detailing the SRL strategies students employ in reflective learning contexts. Conducted as a quantitative descriptive with 53 student participants, the research utilized correlation analysis to examine the interrelationships between various SRL strategies and employed a three-stage qualitative analysis process: data reduction, data presentation, and conclusion drawing. The findings reveal significant positive correlations among SRL strategies, notably between learning responsibility and environmental structuring (r = 0.706), memory strategy and goal setting (r = 0.717), and goal setting and self-evaluation (r = 0.722). The least positive correlation was found between self-evaluation and organizing (r = 0.437). Additional positive relationships were identified between memory strategy and perceived value (r = 0.668), goal setting and value (r = 0.762), self-evaluation and value (r = 0.669), seeking assistance and value (r = 0.763), environmental structuring and value (r = 0.825), learning responsibility and value (r = 0.795), and organizing and value (r = 0.645). Reflective learning stages—comprising the forethought phase, the performance phase as evidenced by students presenting their experiences, and the self-reflection phase during evaluation—highlight the intricate dynamics of students' SRL strategies. This study underscores the positive impact of SRL strategies on learning outcomes, offering insights into the effective application of reflective learning in educational settings.

Abstract 3650: Deep learning-based image cytometry and co-localization index in tumor immune microenvironment

Abstract Background: In pathology, digitizing tissue slides has prompted a remarkable development in image analysis using deep learning. This technological advancement is anticipated to aid in pathological diagnosis and to enhance patient management. Deep learning-based image cytometry (DL-IC) enables accurate cell identification and counting and the acquisition of vast amounts of location information from tissue slides. DL-IC can capture information about the diverse and complex tumor immune microenvironment(TIME) and its constituent cells and help identify biomarkers to predict patient treatment efficacy and prognosis. This study will introduce a spatial interaction map and co-localization index (CLI) for the analysis of TIME using DL-IC. Materials and Methods: Cu-Cyto, a deep learning-based image analysis technology, was used in this study; bit-pattern kernel filtering technology, which can accurately count cells while avoiding the determination of multiple cell counts, was used by Cu-Cyto (Abe T, et al. Anticancer Res. 43:3755, 2023). First, the accuracy of cell counting using Cu-Cyto was evaluated. Second, tumor tissue slides with immunohistochemical (IHC) and hematoxylin-eosin (H&amp;E) staining were prepared from surgical specimens of patients with rectal cancer who had undergone neoadjuvant chemoradiotherapy (NACRT), and the relationship between the co-localization index (CLI) of cancer cells and CD8+T cells and prognosis was investigated. CLI was defined to predict cell- cell interactions on the basis of the relative distances between different cell types (Nagasaka T. PCT/JP 2021/021455). Results: The performances of three versions of Cu-Cyto were evaluated according to their learning stages. In the early stage of learning, the F1 score for immunostained CD8+ T cells (0.343) was higher than that for non-immunostained cells (adenocarcinoma cells [0.040] and lymphocytes [0.002]). In the latest stage of learning, the F1 scores for adenocarcinoma cells, lymphocytes, and CD8+ T cells were 0.589, 0.889, and 0.911, respectively. Next, we examined the correlation of CLI between cancer cells and CD8+ T cells with prognosis: patients with a higher CLI significantly prolonged five-year disease-free survival (P=0.038), while there was no substantial difference in five-year overall survival (P=0.57). Conclusion]: Cu-Cyto performed well in cell determination. In particular, IHC was able to increase the learning efficiencies in the early stages of learning. The CLI calculated using Cu-Cyto ts an objective, reproducible, and innovative quantitative approach for assessing cell-cell interactions, which has been shown to be associated with recurrence-free survival in patients with rectal cancer after NACRT. Its performance is expected to improve even further with continuous learning, and the DL-IC can contribute to the implementation of precision oncology. Citation Format: Tomoki Abe, Kimihiro Yamashita, Toru Nagasaka, Tomosuke Mukoyama, Souichirou Miyake, Yasuhiro Ueda, Masayuki Ando, Yuki Okazoe, Takao Tsuneki, Yukari Adachi, Ryunosuke Konaka, Ryuichiro Sawada, Hironobu Goto, Hiroshi Hasegawa, Shingo Kanaji, Takeru Matsuda, Takumi Fukumoto, Yoshihiro Kakeji. Deep learning-based image cytometry and co-localization index in tumor immune microenvironment [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3650.

Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks

This paper presents a comprehensive empirical investigation into the interactions between various randomization techniques in Deep Neural Networks (DNNs) and their impact on learning performance. It is well-established that injecting randomness into the training process of DNNs, through various approaches, at different stages, is often beneficial for reducing overfitting and improving generalization. Nonetheless, the interactions between randomness techniques such as weight noise, dropout, and many others remain poorly understood. Consequently, it is challenging to determine which methods can be effectively combined to optimize DNN performance. To address this issue, we categorize the existing randomness techniques into four key types: injection of noise/randomness at the data, model structure, optimization or learning stage. We use this classification to identify gaps in the current coverage of potential mechanisms for the introduction of randomness, leading to proposing two new techniques: adding noise to the loss function and random masking of the gradient updates.In our empirical study, we employ a Particle Swarm Optimizer (PSO) for hyperparameter optimization (HPO) to explore the space of possible configurations to determine where and how much randomness should be injected to maximize DNN performance. We assess the impact of various types and levels of randomness for DNN architectures across standard computer vision benchmarks: MNIST, FASHION-MNIST, CIFAR10, and CIFAR100. Across more than 30000 evaluated configurations, we perform a detailed examination of the interactions between randomness techniques and their combined impact on DNN performance. Our findings reveal that randomness through data augmentation and in weight initialization are the main contributors to performance improvement. Additionally, correlation analysis demonstrates that different optimizers, such as Adam and Gradient Descent with Momentum, prefer distinct types of randomization during the training process. A GitHub repository with the complete implementation and generated dataset is available.2

Visible and Infrared Object Tracking Based on Multimodal Hierarchical Relationship Modeling

Visible RGB and Thermal infrared (RGBT) object tracking has emerged as a prominent area of focus within the realm of computer vision. Nevertheless, the majority of existing RGBT tracking methods, which predominantly rely on Transformers, primarily emphasize the enhancement of features extracted by convolutional neural networks. Unfortunately, the latent potential of Transformers in representation learning has been inadequately explored. Furthermore, most studies tend to overlook the significance of distinguishing between the importance of each modality in the context of multimodal tasks. In this paper, we address these two critical issues by introducing a novel RGBT tracking framework centered on multimodal hierarchical relationship modeling. Through the incorporation of multiple Transformer encoders and the deployment of self-attention mechanisms, we progressively aggregate and fuse multimodal image features at various stages of image feature learning. Throughout the process of multimodal interaction within the network, we employ a dynamic component feature fusion module at the patch-level to dynamically assess the relevance of visible information within each region of the tracking scene. Our extensive experimentation, conducted on benchmark datasets such as RGBT234, GTOT, and LasHeR, substantiates the commendable performance of our proposed approach in terms of accuracy, success rate, and tracking speed.

Adaptif Teknologi Dalam Mendukung Penerapan Pembelajaran Digital Dan Literasi Numerasi Pada SMA Swasta Deli Murni Bandar Baru

Community Service Program (PkM) for FKIP students at HKBP Nommensen University in Medan together with the team carried out Adaptive Technology activities to support the implementation of digital learning and numeracy literacy at Deli Murni Private High School. Technology adaptation refers to the process by which an identity, whether an individual, organization, or system, integrates and changes the way they operate or interact with new technology or innovation. Technology will affect the education system in Indonesia, one of which is schools with literacy and numeracy limitations. Numeracy literacy is the fundamental ability to understand, use and apply mathematical concepts in everyday situations. The method of implementing activities is carried out in the stages of survey, socialization, learning, evaluation and documentation. The results of activities carrying out administrative tasks at school using technology such as laptops and computers, completing various files through the school dapodik book, dividing teams, we carry out activities according to school needs including helping guidance and counseling teachers every morning before marching, the school administration center, working on documents and help teachers in doing assignments.

Optimizing flood susceptibility assessment in semi-arid regions using ensemble algorithms: a case study of Moroccan High Atlas

This study explores and compares the predictive capabilities of various ensemble algorithms, including SVM, KNN, RF, XGBoost, ANN, DT, and LR, for assessing flood susceptibility (FS) in the Houz plain of the Moroccan High Atlas. The inventory map of past flooding was prepared using binary data from 2012 events, where “1” indicates a flood-prone area and “0” a non-flood-prone or extremely low area, with 762 indicating flood-prone areas. 15 different categorical factors were determined and selected based on importance and multicollinearity tests, including slope, elevation, Normalized Difference Vegetation Index, Terrain Ruggedness Index, Stream Power Index, Land Use and Land Cover, curvature plane, curvature profile, aspect, flow accumulation, Topographic Position Index, soil type, Hydrologic Soil Group, distance from river and rainfall. Predicted FS maps for the Tensift watershed show that, only 10.75% of the mean surface area was predicted as very high risk, and 19% and 38% were estimated as low and very low risk, respectively. Similarly, the Haouz plain, exhibited an average surface area of 21.76% for very-high-risk zones, and 18.88% and 18.18% for low- and very-low-risk zones respectively. The applied algorithms met validation standards, with an average area under the curve of 0.93 and 0.91 for the learning and validation stages, respectively. Model performance analysis identified the XGBoost model as the best algorithm for flood zone mapping. This study provides effective decision-support tools for land-use planning and flood risk reduction, across globe at semi-arid regions.

Comparing the performance of artificial intelligence learning models to medical students in solving histology and embryology multiple choice questions

IntroductionThe appearance of artificial intelligence language models (AI LMs) in the form of chatbots has gained a lot of popularity worldwide, potentially interfering with different aspects of education, including medical education as well. The present study aims to assess the accuracy and consistency of different AI LMs regarding the histology and embryology knowledge obtained during the 1st year of medical studies. MethodsFive different chatbots (ChatGPT, Bing AI, Bard AI, Perplexity AI, and ChatSonic) were given two sets of multiple-choice questions (MCQs). AI LMs test results were compared to the same test results obtained from 1st year medical students. Chatbots were instructed to use revised Bloom’s taxonomy when classifying questions depending on hierarchical cognitive domains. Simultaneously, two histology teachers independently rated the questions applying the same criteria, followed by the comparison between chatbots’ and teachers’ question classification. The consistency of chatbots’ answers was explored by giving the chatbots the same tests two months apart. ResultsAI LMs successfully and correctly solved MCQs regarding histology and embryology material. All five chatbots showed better results than the 1st year medical students on both histology and embryology tests. Chatbots showed poor results when asked to classify the questions according to revised Bloom’s cognitive taxonomy compared to teachers. There was an inverse correlation between the difficulty of questions and their correct classification by the chatbots. Retesting the chatbots after two months showed a lack of consistency concerning both MCQs answers and question classification according to revised Bloom’s taxonomy learning stage. ConclusionDespite the ability of certain chatbots to provide correct answers to the majority of diverse and heterogeneous questions, a lack of consistency in answers over time warrants their careful use as a medical education tool.