Learning Approach Research Articles

Triple-loop learning as a framework for advancing health systems science in medical education: a transformational change approach

Purpose The American Medical Association has recently adopted health systems science (HSS) as the third pillar of medical education to provide comprehensive and holistic patient care. The purpose of this paper is to propose a novel organizational learning perspective in considering how medical schools can facilitate a transformational HSS curriculum change. Design/methodology/approach This is a conceptual paper seeking to present triple-loop learning as a potential approach to HSS curriculum change. Findings Due to its potential for structural accountability and sustainability stemming from the inclusion of diverse voices, the authors argue that HSS curriculum change, guided by the principles of triple-loop learning, is likely to lead to the development of medical curricula that are more adaptive and responsive to the constantly changing health-care landscape. The authors advocate for the deliberate inclusion of stakeholders who have historically been excluded or marginalized in the HSS curriculum change process, such as patients and those in sentinel roles (e.g. nurses, social workers). The authors also suggest an integrated, multilevel transformation that involves collaboration among medical schools, accreditation organizations, licensing boards and health-care systems. Originality/value To the best of the authors’ knowledge, this paper represents the first attempt to apply the theory of triple-loop learning in the context of HSS curriculum change. It highlights how this critical systemic learning approach uniquely contributes to HSS curriculum change, and subsequently to the necessary, larger cultural changes demanded in medical education as a whole.

A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts

A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts

Strategic use of machine translation

Abstract The development of generative artificial intelligence (AI) and its associated tools has revolutionised the learning and use of foreign languages (L2). One such tool is machine translation (MT), which has become increasingly popular among university students worldwide, spurring research on MT use in L2 writing. However, previous research has primarily focused on the writing products of intermediate or advanced L2 learners, neglecting the writing process with MT of students with limited L2 proficiency. Therefore, this case study aimed to qualitatively explore how the Common European Framework of Reference for Languages (CEFR) A2 university students employ strategies for L2 writing with MT and how their strategies change after strategy instruction. Seven participants completed writing tasks on a PC before, immediately after, and four weeks after three one-hour out-of-class instruction sessions based on the Strategic Content Learning (SCL) approach. Their writing process was screen-recorded, followed by stimulated recall interviews to elicit their strategies, which were coded and categorised using a framework by O’Malley and Chamot (1990). The results showed an increase in students’ elaborate use of strategies after instruction. In particular, strategy clusters were observed for all participants, demonstrating their cognitive engagement in the writing process. Furthermore, first-language (L1)-related strategies were used more frequently post-instruction, indicating learners’ efforts to create translation-friendly L1 input for MT. The findings suggest that teaching MT-use strategies is crucial to fostering learners’ active engagement in the L2 writing process in a technology-enhanced learning environment.

A novel prediction model for the prognosis of non-small cell lung cancer with clinical routine laboratory indicators: a machine learning approach

A novel prediction model for the prognosis of non-small cell lung cancer with clinical routine laboratory indicators: a machine learning approach

A Dataset of 3M Single-DOF Planar 4-, 6-, and 8-Bar Linkage Mechanisms With Open and Closed Coupler Curves for Machine Learning-Driven Path Synthesis

Abstract In recent years, there has been a strong interest in applying machine learning techniques to path synthesis of linkage mechanisms. However, progress has been stymied due to a scarcity of high-quality datasets. In this article, we present a comprehensive dataset comprising nearly three million samples of 4-, 6-, and 8-bar linkage mechanisms with open and closed coupler curves. Current machine learning approaches to path synthesis also lack standardized metrics for evaluating outcomes. To address this gap, we propose six key metrics to quantify results, providing a foundational framework for researchers to compare new models with existing ones. We also present a variational autoencoder-based model in conjunction with a k-nearest neighbor search approach to demonstrate the utility of our dataset. In the end, we provide example mechanisms that generate various curves along with a numerical evaluation of the proposed metrics.

Deep Encodings vs. Linguistic Features in Lexical Complexity Prediction

AbstractIn this work, we present a novel approach to lexical complexity prediction (LCP) that combines diverse linguistic features with encodings from deep neural networks. We explore the integration of 23 handcrafted linguistic features with embeddings from two well-known language models: BERT and XLM-RoBERTa. Our method concatenates these features before inputting them into various machine learning algorithms, including SVM, Random Forest, and fine-tuned transformer models. We evaluate our approach using two datasets: CompLex for English (a high-resource language) and CLexIS2 for Spanish (a relatively low-resource language in ), allowing us to study performance issues from a cross-lingual perspective. Our experiments involve different combinations of linguistic features with encodings from pretrained deep learning models, testing both token-based and sequence-related encodings. The results demonstrate the effectiveness of our hybrid approach. For the English CompLex corpus, our best model achieved a mean absolute error (MAE) of 0.0683, representing a 29.2% improvement over using linguistic features alone (MAE 0.0965). On the Spanish CLexIS2 corpus, we achieved an MAE of 0.1323, a 19.4. These findings show that handcrafted linguistic features play a fundamental role in achieving higher performance, particularly when combined with deep learning approaches. Our work suggests that hybrid approaches should be considered over full end-to-end solutions for LCP tasks, especially in multilingual contexts.

Using machine learning approaches for predicting the compressive strength of ultra-high-performance concrete with SHAP analysis

Using machine learning approaches for predicting the compressive strength of ultra-high-performance concrete with SHAP analysis

Detection of Defects in Polyethylene and Polyamide Flat Panels Using Airborne Ultrasound-Traditional and Machine Learning Approach

This paper presents the use of noncontact ultrasound for the nondestructive detection of defects in two plastic plates made of polyamide (PA6) and polyethylene (PE). The aim of the study was to: (1) assess the presence of defects as well as their size, type, and orientation based on the amplitudes of Lamb ultrasonic waves measured in plates made of polyamide (PA6) and polyethylene (PE) due to their homogeneous internal structure, which mainly determined the selection of such model materials for testing; and (2) verify the possibilities of building automatic quality control and defect detection systems based on ML based on the results of the above-mentioned studies within the Industry 4.0/5.0 paradigm. Tests were conducted on plates with generated synthetic defects resembling defects found in real materials such as delamination and cracking at the edge of the plate and a crack (discontinuity) in the center of the plate. Defect sizes ranged from 1 mm to 15 mm. Probes at 30 kHz were used to excite Lamb waves in the slab material. This method is sensitive to the slightest changes in material integrity. A significant decrease in signal amplitude was observed, even for defects of a few millimeters in length. In addition to traditional methods, machine learning (ML) was used for the analysis, allowing an initial assessment of the method’s potential for building cyber-physical systems and digital twins. By training ML models on ultrasonic data, algorithms can distinguish subtle differences between signals reflected from normal and defective areas of the material. Defect types such as voids, cracks, or weak bonds often produce distinct acoustic signatures, which ML models can learn to recognize with high accuracy. Using techniques like feature extraction, ML can process these high-dimensional ultrasonic datasets, identifying patterns that human inspectors might overlook. Furthermore, ML models are adaptable, allowing the same trained algorithms to work on various material batches or panel types with minimal retraining. This combination of automation and precision significantly enhances the reliability and efficiency of quality control in industrial manufacturing settings. The achieved accuracy results, 0.9431 in classification and 0.9721 in prediction, are comparable to or better than the AI-based quality control results in other noninvasive methods of flat surface defect detection, and in the presented ultrasonic method, they are the first described in this way. This approach demonstrates the novelty and contribution of artificial intelligence (AI) methods and tools, significantly extending and automating existing applications of traditional methods. The susceptibility to augmentation by AI/ML may represent an important new property of traditional methods crucial to assessing their suitability for future Industry 4.0/5.0 applications.

Increasing phosphorus loss despite widespread concentration decline in US rivers

The loss of phosphorous (P) from the land to aquatic systems has polluted waters and threatened food production worldwide. Systematic trend analysis of P, a nonrenewable resource, has been challenging, primarily due to sparse and inconsistent historical data. Here, we leveraged intensive hydrometeorological data and the recent renaissance of deep learning approaches to fill data gaps and reconstruct temporal trends. We trained a multitask long short-term memory model for total P (TP) using data from 430 rivers across the contiguous United States (CONUS). Trend analysis of reconstructed daily records (1980–2019) shows widespread decline in concentrations, with declining, increasing, and insignificantly changing trends in 60%, 28%, and 12% of the rivers, respectively. Concentrations in urban rivers have declined the most despite rising urban population in the past decades; concentrations in agricultural rivers however have mostly increased, suggesting not-as-effective controls of nonpoint sources in agriculture lands compared to point sources in cities. TP loss, calculated as fluxes by multiplying concentration and discharge, however exhibited an overall increasing rate of 6.5% per decade at the CONUS scale over the past 40 y, largely due to increasing river discharge. Results highlight the challenge of reducing TP loss that is complicated by changing river discharge in a warming climate.

Machine Learning Enabled Compact Frequency‐Tunable Triple‐Band Hexagonal‐Shaped Graphene Antenna for THz Communication

ABSTRACTIn this article, a compact triple‐band frequency‐tunable (FT) hexagonal‐shaped graphene antenna through a machine learning (ML) approach for terahertz (THz) application is presented. The proposed THz antenna is designed on a polyamide () substrate with a thickness of 10 μm, and graphene is used as an antenna radiator. The size of the substrate is 38 × 46 μm2. The FT is achieved by changing the chemical potential of graphene material. The performance of the proposed THz antenna has been investigated, and the impacts of several conducting materials like gold, aluminum, copper, and graphene and dielectric materials like Rogers RT/duroid 5880, polyamide, quartz, and SiO2 are explored. The proposed THz antenna provides three operating bands. The frequency of operation in Band‐1 is 2.51–5.05 THz, Band‐2 is 5.99–7.43 THz, and Band‐3 is 7.94–9.63 THz. The bandwidth in Band‐1, Band‐2, and Band‐3 are 2.54, 1.44, and 1.69 THz, respectively. The % of impedance bandwidth in Band‐1, Band‐2, and Band‐3 are 67.19%, 24.02%, and 21.28% respectively. The proposed antenna has a maximum peak gain of 5 dBi. The proposed antenna is optimized through various ML algorithms like random forest (RF), extreme gradient boosting (XGB), K‐nearest neighbor (KNN), decision tree (DT), and artificial neural network (ANN). The RF algorithm gives more than 99% accuracy compared to other ML algorithms and accurately predicts the S11 of the proposed antenna. The proposed THz antenna would be suitable for applications related to imaging, medical, sensing, and ultra‐speed short‐distance communication applications in the THz region.

Abstract IA025: Targeting the gut microbiome for cancer immunotherapy

Abstract Growing evidence suggests that the gut microbiota modulates the efficacy and toxicity of cancer therapy, most notably immunotherapy and its immune-related adverse effects. The impaired response to immunotherapy in patients treated with antibiotics supports this role of the microbiota. Until recently, results pertaining to the identification of the microbial species responsible for these effects were incongruent, and relatively few studies analyzed the underlying mechanisms. Gut microbial communities (microbiotypes) with non-uniform geographic distribution were associated with favorable and unfavorable outcomes, contributing to discrepancies between cohorts Now, a better understanding of the taxonomy of the species involved and of their mechanisms of action has been achieved. Defined bacterial species have been shown to promote a response to immune checkpoint inhibitors through the production of different products or metabolites, although a suppressive effect of Gram(-) bacteria may be dominant in some unresponsive patients. Machine learning approaches trained on patients’ microbiota composition can predict the ability of patients to respond to immunotherapy with some accuracy. Thus, the interest in modulating the microbiota composition to improve patients’ responsiveness to therapy has been mounting. Our data of a fecal microbiota transfer clinical trial in anti-PD1 refractory melanoma patients has provided clinical proof of concept of the possibility to target the gut microbiota composition in cancer therapy. Also, both in clinical studies and in experimental animals, diets rich in fibers improve the response to immunotherapy by modifying the gut microbiome suggesting the possibility of dietary approaches to target the microbiota composition in cancer therapy. However, while many early clinical studies have analyzed the association of the microbiota composition with the response to anti-PD-1 in cancer patients, emerging evidence suggests that the association may be context dependent and different types of mono or combination immunotherapies may be differentially regulated by the microbiota, Thus, a more personalized approach depending original gut microbiota composition of the patients and the type of immunotherapy protocol selected may be necessary for optimal clinical results. Citation Format: Giorgio Trinchieri. Targeting the gut microbiome for cancer immunotherapy [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Tumor-body Interactions: The Roles of Micro- and Macroenvironment in Cancer; 2024 Nov 17-20; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2024;84(22_Suppl):Abstract nr IA025.

Abstract B010: Improving pancreatic cancer image classification with transfer learning: CD45 vs. PANCK

Abstract Pancreatic ductal adenocarcinoma (PDAC) is known for its high aggressiveness and is the fourth most common cause of death of cancer-related death in the United States. It is highly malignant and often goes undiagnosed until advanced stages due to its late-onset symptoms, resulting in poor prognosis. Using quantitative analyses of histological features, such as the expression of prognostic biomarker, can provide valuable insight to guide treatment decisions, monitor disease progression and predict outcomes. Previous researchers have found that CD45 and PANCK play a huge role in characterizing the tumor microenvironment of PDAC. One study using single-cell RNA sequencing compared the microenvironments of healthy pancreata and pancreatic tumors, revealing differences in cellular composition. Tumor samples showed a higher proportion of immune cells, including CD45+ cells, compared to heathy samples and utilized PANCK to differentiate between epithelial and non-epithelial cells. This study aims to enhance the accuracy of classifying pancreatic cancer pathological images based on prognostic markers using transfer learning techniques. We curated and pre-processed a dataset of pancreatic cancer pathological images with different prognostic markers. Using the pre-trained convolutional neural network (CNN) model VGG16, we fine-tuned it with our dataset to better differentiate between two prognostic markers, CD45 and PANCK. The model's performance was evaluated using a similarity matrix to illustrate distinctions among the two prognostic markers. Our results demonstrate that the transfer learning approach significantly improves classification accuracy, achieving confusion matrix validation results of 90% between CD45 and PANCK prognostic markers. SSIM values were relatively low, highlighting the ability of our model to differentiate between the two prognostic markers. The low SSIM value also shows variability within the two prognostic markers, indicating heterogeneity in structural changes due to pancreatic cancer. These findings indicate that transfer learning can be a powerful tool for improving the classification of pathological images and that there is notable variability in the structural features associated with different prognostic markers in pancreatic cancer. Citation Format: Miracle Thomas. Improving pancreatic cancer image classification with transfer learning: CD45 vs. PANCK [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Tumor-body Interactions: The Roles of Micro- and Macroenvironment in Cancer; 2024 Nov 17-20; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2024;84(22_Suppl):Abstract nr B010.

Differentiated Learning Models: Students’ Learning Style, Readiness, and Interest in Learning Regarding the Results of Fiqh

<em>The differentiation learning model is a novel approach that caters to the demands of the 21st- century education system. Studies conducted by Indonesian scholars on this model are scarce, with limited focus on its impact on students' cognitive abilities and metacognitive awareness. Therefore, this study seeks to investigate the impact of incorporating a differentiated learning approach founded on the learning preferences, preparedness, and engagement of pupils on Fiqh's academic performance. An explanatory survey technique employing the Stratified Random Sampling methodology is utilized in this research. The sample comprises all fifth-grade students of the State Islamic Primary School in Tulungagung Regency, amounting to a total of 507 learners. The study's sample comprises four randomly selected State Islamic Primary Schools from the seven Tulungagung Regency, with a total of 276 students studying Fiqh. The data collection instruments used include test sheets for learning outcomes, notes on creative thinking skills, and motivation questionnaires. The data is then analyzed using a two-way Analysis of Variance (ANOVA) with a significance level of 5%. The results of the research indicate that: (1) There is no discernible disparity in Fiqh learning outcomes based on learning style. (2) There is no disparity in Fiqh learning outcomes based on students’ learning readiness. (3) Disparities in Fiqh learning outcomes based on students’ learning interests exist. (4) A noteworthy interaction exists between the implementation of differentiation learning aspects of learning styles, learning readiness, and students’ learning interests on Fiqh learning outcomes. The findings of this study suggest that the differentiation learning model provides an alternative approach to learning that addresses the needs of the modern era.</em>

Data‐driven framework for predicting the sorption capacity of carbon dioxide and methane in tight reservoirs

AbstractAs energy demand continues to rise and conventional fuel sources dwindle, there is growing emphasis on previously overlooked reservoirs, such as tight reservoirs. Shale and coal formations have emerged as highly attractive options due to their substantial contributions to global gas reserves. Enhanced shale gas recovery (ESGR) and enhanced coalbed methane recovery (ECBM) based on gas injection are advanced techniques used to increase the extraction of gas from shale and coal formations. One of the key challenges associated with these formations and their enhanced recovery methods is accurately predicting the sorption process and its profile. This is crucial because it affects how methane (CH4) and carbon dioxide (CO2) are stored and released from the rock, and it significantly impacts the evaluation of gas content and the potential productivity of these formations. Due to the high cost of experimental procedures and the moderate accuracy of existing predictive approaches, this study proposes various cheap and consistent data‐driven schemes for predicting the sorption of CH4 and CO2 in shale and coal formations. In this regard, three intelligent models, including generalized regression neural network (GRNN), radial basis function neural network (RBFNN), and categorical boosting (CatBoost), were taught and tested using more than 3800 real measurements of CH4 and CO2 sorption in shale and coal formations. To find automatically their appropriate control parameters and improve their prediction ability, RBFNN and CatBoost were evolved using grey wolf optimization (GWO). The obtained results exhibited the encouraging prediction capabilities of the suggested models. In addition, it was found that CatBoost‐GWO is the most accurate scheme with total root mean square (RMSE) and determination coefficient (R2) of 0.1229 and 0.9993 for CO2 sorption, and 0.0681 and 0.9970 for CH4 sorption, respectively. Additionally, this approach demonstrated its physical validity by respecting the real sorption tendencies with respect to operational parameters. Furthermore, the CatBoost‐GWO model outperforms recently published machine learning approaches. Lastly, the findings of this study offer a significant contribution by demonstrating that the suggested model can greatly improve the ease of estimating CO2 and CH4 sorption in tight formations, thereby facilitating the simulation of other parameters related to this process. © 2024 Society of Chemical Industry and John Wiley & Sons, Ltd.

Spatial Prediction of Soil Continuous and Categorical Properties Using Deep Learning Approaches for Tamil Nadu, India

Large-scale mapping of soil resources can be crucial and indispensable for several of the managerial applications and policy implications. With machine learning models being the most utilized modeling technique for digital soil mapping (DSM), the implementation of model-based deep learning methods for spatial soil predictions is still under scrutiny. In this study, soil continuous (pH and OC) and categorical variables (order and suborder) were predicted using deep learning–multi layer perceptron (DL-MLP) and one-dimensional convolutional neural networks (1D-CNN) for the entire state of Tamil Nadu, India. For training the deep learning models, 27,098 profile observations (0–30 cm) were extracted from the generated soil database, considering soil series as the distinctive stratum. A total of 43 SCORPAN-based environmental covariates were considered, of which 37 covariates were retained after the recursive feature elimination (RFE) process. The validation and test results obtained for each of the soil attributes for both the algorithms were most comparable with the DL-MLP algorithm depicting the attributes’ most intricate spatial organization details, compared to the 1D-CNN model. Irrespective of the algorithms and datasets, the R2 and RMSE values of the pH attribute ranged from 0.15 to 0.30 and 0.97 to 1.15, respectively. Similarly, the R2 and RMSE of the OC attribute ranged from 0.20 to 0.39 and 0.38 to 0.42, respectively. Further, the overall accuracy (OA) of the order and suborder classification ranged from 39% to 67% and 35% to 64%, respectively. The explicit quantification of the covariate importance derived from the permutation feature importance implied that both the models tried to incorporate the covariate importance with respect to the genesis of the soil attribute under study. Such approaches of the deep learning models integrating soil–environmental relationships under limited parameterization and computing costs can serve as a baseline study, emphasizing opportunities in increasing the transferability and generalizability of the model while accounting for the associated environmental dependencies.

Deep Learning Approach for Suspicious Activity Detection from Surveillance Video

The present generation seeks ways to live their lives free of fear. This often prompts the need for enhanced law enforcement and security systems. Suspicion activity recognition in surveillance footage has become an essential component in modern security systems, focused around the problem of recognizing inappropriate behaviors without too much human time. The advent of deep learning has made an impact in computer vision tasks within such a way the real-time detection by the evaluation of large amounts of video footage becomes realistic. In this context the paper presents a model in which deep learning, particularly Convolutional Neural Networks (CNNs), are utilized for the behavioral pattern recognition from security footage. In addition, it also improves the efficacy of detection and reduces the shortcomings associated with these systems where only the post-event analysis is performed manually or automatically. In this paper, we demonstrate a novel IP model that analyzes live video and performs normal-suspicious–threat triage in real-time. Results indicate the validity of the method in different environmental and illumination conditions. An important objective that this system is designed for is to change the way security is practiced and delivered in today’s intelligent systems providing actionable intelligence and the ability to prevent threats rather than just respond to them making this a high growth opportunity for marketing high-risk and sensitive areas.

Evaluating work placement supervisors’ ratings of Master’s in research psychology students at an open and distance e-learning institution in South Africa

This paper examines the dataset of work placement supervisors’ feedback from 2014 to 2017 on the skillset of Master in Research Psychology students during their first and second placement periods. A total of 47 placement feedback reports were analysed. The analysis included frequency counts and qualitative content analysis using Microsoft (MS) Excel software. The study reveals that placement supervisors place significant value on soft skills, notably a willingness to learn, and frequently rate students favourably on interpersonal skills. The results highlight the importance of viewing placement supervisors as co-educational partners. By evaluating supervisors' ratings of research psychology students on work placement holds significant value in improving educational programs, enhancing student outcomes, aligning with employer expectations, and contributing to the broader understanding of work-integrated learning in research psychology. For students, it entails identifying areas of strength and areas for improvement in their performance. For the university program, this feedback can inform teaching and learning approaches by providing insights into the specific skills, competencies, and knowledge that students need to develop during their program. It can also help tailor feedback and support by understanding supervisors' feedback, leading to more effective guidance and constructive feedback for students. For the placement organisations, the research can contribute to supervisor training and development, ensuring they have the necessary skills to guide and evaluate students, while also improving work placement design and coordination to align with program learning outcomes and provide meaningful experiences for students.

Machine learning prediction of brain metastasis invasion pattern on brain MRI scans

Abstract Background Brain metastasis invasion pattern (BMIP) is an emerging biomarker associated with recurrence-free and overall survival in patients, and differential response to therapy in preclinical models. Currently, BMIP can only be determined from the histopathological examination of surgical specimens, precluding its use as a biomarker prior to therapy initiation. The aim of this study was to investigate the potential of machine learning (ML) approaches to develop a non-invasive magnetic resonance imaging (MRI)-based biomarker for BMIP determination. Methods From an initial cohort of 329 patients, a subset of 132 patients met inclusion criteria for this retrospective study. We evaluated the ability of an expert neuroradiologist to reliably predict BMIP. Thereafter, the dataset was randomly divided into training/validation (80% of cases) and test subsets (20% of cases). Ground truth for BMIP was histopathologic evaluation of resected specimens. Following MRI sequence co-registration, advanced feature extraction techniques deriving hand-crafted radiomic features with traditional ML classifiers and convolution-based deep learning (CDL) models were trained and evaluated. Different ML approaches were used individually or using ensembling techniques to determine the model with the best performance for BMIP prediction. Results Expert evaluation of brain MRI scans could not reliably predict BMIP, with an accuracy of 44-59% depending on the semantic feature used. Among the different ML and CDL models evaluated, the best performing model achieved an accuracy of 85% and an F1-score of 90%. Conclusion ML approaches can effectively predict BMIP, representing a non-invasive MRI-based approach to guide management of patients with brain metastases.

Deep Learning-Based Identification of Immoral Posts on Social Media Using Fine-tuned Bert Model

The propagation of immoral content on social media poses substantial worries to online societal well-being and communication standards. While beneficial, traditional machine learning (ML) methods fall short of capturing the difficulty of textual and sequential data. This work reports this gap by suggesting a deep learning-based technique for detecting immoral posts on social media. The proposed model presents a fine-tuned Bidirectional Encoder representation from Transformers (BERT) with word embedding methods. Word2Vec and Global Vectors for Word Representation (GloVe) are employed to improve the identification of immoral posts on social media platforms to advance detection accuracy and strength. The incentive behind this study stems from the increasing demand for more sophisticated methods to struggle with damaging content. The proposed model is considered to capture the complicated patterns and semantic nuances in immoral posts by decreasing the dependence on manual feature engineering. The model is trained and assessed using benchmark datasets containing SARC and HatEval, which deliver a detailed set of labelled user-generated posts. The proposed model shows the best performance compared to traditional ML approaches. The fine-tuned Bert-based Word2Vec embeddings achieved a precision of 95.68%, recall of 96.85 %, and F1 scores of 96.26% on the SARC dataset. Fine-tuned Bert-based GloVe on the HatEval dataset achieved superior precision of 96.65, recall of 97.75, and F1-score of 97.20. The proposed results highlight the potential of the deep learning (DL) approach and fine-tuned BERT models, considerably refining the detection of unethical content on social networks.

SmartStudy-Learning Path Recommender system using DS and ML

Learning Path Recommender Systems (LPRS) utilize machine learning and data-driven approaches to personalize educational experiences, adapting content sequences based on individual learners’ needs and progress. With the rising demand for tailored learning, LPRS have emerged as vital tools to guide students through educational content, enhancing engagement and achievement. This review covers state-of-the-art algorithms, including collaborative filtering and reinforcement learning, used in LPRS to optimize learning paths. We discuss model accuracy, user interaction data, and adaptive feedback mechanisms, providing insights into the potential of LPRS to improve learning outcomes