The phenomenal growth of digital learning platforms has brought new learner engagement and retention challenges to higher education. This study proposes a framework that integrates game mechanics—leveling systems, badges, and timely feedback—with artificial intelligence (AI)-driven personalization to meet the challenges of enhanced adaptability, motivation, and learning outcomes in online environments. Key design elements were identified through literature reviews and consultations with instructional design experts, leading to the development an adaptive learning platform prototype. The prototype underwent an eight-week pilot study with 250 Prince Sattam Bin Abdulaziz University (PSAU) students randomly assigned to a control group (non-adaptive system) or an experimental group (adaptive system). Data sources included pre- and post-tests, platform engagement analytics, and learner perception surveys. The results showed that the adaptive group outperformed the control group in the post-test scores (M = 85.2, SD = 6.4 vs. M = 78.5, SD = 7.2) and motivation levels (M = 4.2, SD = 0.7 vs. M = 3.6, SD = 0.8). Additionally, 82% of the adaptive group achieved mastery-level performance compared to 64% in the control group. These findings demonstrate the potential of integrating game mechanics and AI-driven personalization to transform digital learning, offering a roadmap for scalable, data-driven adaptive platforms. Future research will address long-term retention and diverse subject applications.

The rising trend of hate speech on the internet is being major concern to the internet security and societal coexistence, which will requires efficient automated detection tools. As much as different machine learning strategies have been suggested, the issue of the high accuracy using limited data still remains a challenge. This paper introduces a collective detecting frame of hate speech that was tested on the Ethos Binary dataset. Various machine learning classifiers such as K-Nearest Neighbor, Naive Bayes, Logistic Regression, and Decision Tree are used with pre-trained GloVe word embeddings in order to extract semantic representations of textual data. The models are also trained and tested in various hyperparameter configurations, to be robust. The experimental findings indicate that Decision Tree classifier is much better than other models, with a precision of 87, recall of 93, F1-score of 90 and an overall accuracy of 91. The results have shown that an ensemble learning approach with embedding techniques has the potential to greatly increase the performance of hate speech detection. This work helps to enhance viable and scalable solutions to the content of moderating dangerous content online.

Early confirmation of fetal cardiac activity is a critical component of first-trimester prenatal care. Maternal obesity may reduce the diagnostic accuracy of transabdominal ultrasound (TAUS) due to soft tissue attenuation. Objective: To compare the effectiveness of transvaginal ultrasound (TVUS) and transabdominal ultrasound in detecting fetal heartbeat during 5–8 weeks of gestation in obese women. Methods: A cross-sectional study was conducted on 71 obese pregnant women between 5–8 weeks of gestation at a diagnostic center in Kot Addu. All participants underwent both TAUS and TVUS examinations. Fetal heart rate (FHR), gestational sac visualization, and crown-rump length (CRL) were recorded. Data were analyzed using SPSS, including descriptive statistics, correlation, regression, chi-square, and t-tests. Results: TVUS demonstrated a higher mean detection rate (M = 1.82, variance = 0.152) compared to TAUS (M = 1.56, variance = 0.249). Normal fetal heart rate was observed in 67.6% of cases, while 23.9% showed no detectable heartbeat. TAUS failed to detect fetal cardiac activity in 56.3% of cases. A moderate positive correlation (r = 0.299) was found between gestational age and fetal visualization. Statistical analysis confirmed significant associations between fetal observation levels and ultrasound modality (p < 0.05).Conclusion: Transvaginal ultrasound is significantly more reliable than transabdominal ultrasound for detecting fetal heartbeat during early gestation in obese women. TVUS should be considered the preferred imaging modality in this population to improve early pregnancy assessment accuracy.