In this work we have studied the criteria for assessing the quality of educational games and their impact on student learning outcomes by designing two experiments that were conducted in a duration of total of 6 years. The first experiment involves students in their final year of high school studies and the second on first year students in higher education. Our main results have shown that in comparison with traditional methods in education, teaching with the use of educational games increases the degree of mastering of educational material. It is also observed to increase the involvement and motivation of students to perform educational tasks by significantly reducing the time that will be required for reinforcement of the passed material. Additionally, it tends to cause less fatigue and holds their concentration much longer. Based on the results of our research, we have also identified the main criteria for evaluating the effectiveness of educational games. Our results suggest that a robust and comprehensive integration of educational games into the learning process will significantly improve the quality of education at all levels.
This research paper proposes an improved deep learning model for classifying tents in street bazaars, comparing a custom Convolutional Neural Network (CNN) with EfficientNetB0. This is a critical task for market organization with a tent classification, but manual methods in the past have been inefficient. Street bazaars represent a vital economic hub in many regions, yet their unstructured nature poses significant challenges for the automated classification of market infrastructure, such as tents. In Kyrgyzstan, more than a quarter of the country's GDP is derived from bazaars. While CNNs have been widely applied to object recognition, their application to bazaar-specific tasks remains underexplored. Here, we build upon our original approach by training on an extended set of ${1 2 6}$ original photographs that were augmented to generate additional images. This dataset is publicly available for download on Kaggle. A variety of performance metrics, such as accuracy, precision, recall, F1 score, and mean average precision (mAP), were used to assess the models comparatively, providing a more extensive analysis of classification performance. The results show that the CNN custom model achieved 92.8% accuracy, and EfficientNetB0 showed ${9 8. 4 \%}$ accuracy results, confirming the effectiveness of transfer learning in the bazaar image classification. Also, when analyzing the confusion matrix, the analysis reveals the weaknesses and strengths of each model. These findings suggest that using a pre-trained model such as EfficientNetB0 significantly improves classification accuracy and generalization.
Image processing integrated into healthcare facilitates screening to identify and prevent the spread of infections and is used to enhance decision-making processes. LungPrecheck.io is a platform that offers advanced diagnostics through the use of automated X-ray analysis, with the aim of the detection and treatment of lung diseases. The tool incorporates more accurate and effective computer vision models to improve the efficiency of diagnosing TB, pneumonia, and COVID-19. Relying on manual interpretation significantly lengthens the duration of the work and increases the chances of human error. LungPrecheck.io overcame these boundaries by automating the detection of diverse abnormalities in lung radiographs, simultaneously fostering quick actions to identify disease progression and informed decisions by healthcare professionals.
The Arabic language has many features such as the phonology and the syntax that make it an easy language for developing automatic speech recognition systems. This paper presents a pronunciation analysis system designed to assist Quran learners in Kyrgyzstan’s madrasas and online platforms. Speech recognition is a captivating process that revolutionizes human-computer interactions, allowing us to interact and control machines through spoken commands. The foundation of speech recognition lies in understanding a given language’s linguistic and textual characteristics. The system records 3-second audio clips, such as “Bismillahir Rahmanir Rahim,” removes noise, segments them into phonetic units (e.g., “Bism,” “Allah”), and evaluates accuracy using a Support Vector Machine (SVM) classifier trained on recordings from QuranicAudio. Feedback is also given in percent so that students can study by themselves. Using Python, Streamlit, Librosa, and scikit-learn, the system has 90–95% percent accuracy identifying correct pronunciation and 60–70% for the incorrect one. The novelty of this work is in combining machine learning based with real hafiz objective recordings, to overcome an absence of available tools for learning Quran pronunciation. Upcoming we plan to extend to more surahs, such as Al-Fatiha and also grow the data size in order to improve accuracy.