Developing countries are faced with social and economic challenges, including the emergence and proliferation of slums. Slum detection and localization methods typically rely on regular topographic surveys or on visual identification of high-resolution spatial satellite images, as well as socio-environmental surveys from land surveys and general population censuses. Yet, they consume so much time and effort. To overcome these problems, this paper exploits well-known seven pretrained models using transfer learning approaches such as MobileNets, InceptionV3, NASNetMobile, Xception, VGG16, EfficientNet, and ResNet50, consecutively, on a smaller dataset of medium-resolution satellite imagery. The accuracies obtained from these experiments, respectively, demonstrate that the top three pretrained models achieve 98.78%, 97.9%, and 97.56%. Besides, MobileNets have the smallest memory sizes of 9.1 Mo and the shortest latency of 17.01 s, which can be implemented as needed. The results show the good performance of the top three pretrained models to be used for detecting and localizing slum housing in northern Morocco.
The purpose behind this paper research is to localize and detect, for the first time, three types of shantytowns that can exist in both urban and rural areas in Morocco. The reason why we have conducted this study is the absence of diversity slum mapping in the form of dynamic GIS data, which can be a part of national development strategies to tackle the risk of further proliferation of shantytowns. Therefore, we first create a new database integration from five countries whose content contains 1366 high-resolution patches of 224 × 224 pixels divided into five classes: two types of “Urban Slum”, one type of “Rural Slum”, “Formal Buildings”, and non-built-up area. Second, we suggest employing a variety of performance metrics to come up with the best transfer learning-based models for the unfreezing stage. The study reveals that by handling the unfreezing of the front layers, we can produce a reliable new model where one condition is fulfilled, namely, where high-frequency dissimilarities have arisen between the target and the source datasets. Quantitative results of these methodologies show that our dataset and our unfreezing strategy for the mobilenetv2 model are more accurate compared to other competing models. This new model can localize all possible changes in morphology and shape among the three-slum types with state-of-the-art performance that reaches an overall accuracy of 98.17%, a loss of 0.062, and a kappa score of 97.71%. Our dataset and the code will be publicly available at the github 1 to share our results.
Personalized learning is challenging because students have diverse backgrounds, abilities, needs, and traditional teaching often lacks timely, tailored support. This study introduces an AI tutoring system powered by ChatGPT, designed to provide adaptive, context-aware educational assistance. The system uses conversational interfaces, domain-specific prompts, and learner modeling to adjust dynamically to each student's progress and misconceptions. An experimental study with high school and early university students showed that the system significantly improved learner engagement, comprehension, and efficiency. Users appreciated the personalized explanations and adaptive responses, which boosted their motivation and deeper understanding of the material. These findings demonstrate the potential of AI-powered tutoring systems to enhance personalized education by offering scalable, effective, and engaging learning experiences suitable for diverse learners and contexts. This approach could help overcome limitations of traditional education and support individualized learning .
The proliferation of fake news threatens data integrity and public trust, challenging the foundations of modern data-driven systems. This chapter explores how Generative AI, particularly large language models (LLMs), can enhance fake news detection and support trustworthy data architectures. We review key techniques in misinformation detection and analyze the emerging role of GenAI in enabling automated content validation, explanation generation, and credibility assessment. The integration of these models into data pipelines introduces new opportunities but also raises concerns such as hallucinations, bias propagation, and ethical risks. We outline the main challenges and propose future research directions to design autonomous, explainable, and resilient systems capable of mitigating misinformation in real time while upholding transparency and data governance principles.
The rapid advancement of artificial intelligence has catalyzed the emergence of intelligent chatbots as pivotal tools in higher education. Initially deployed for administrative tasks, these conversational agents have evolved into sophisticated virtual advisors that support personalized learning by adapting to individual student needs. This chapter examines the role of chatbots as intelligent advisors, highlighting their capabilities to provide context-aware guidance, real-time feedback, and motivational support. It explores the pedagogical benefits of integrating chatbots into academic environments, including enhanced learner autonomy, inclusivity, and scalability. The discussion also addresses key challenges such as data privacy, ethical considerations, and technological limitations. Finally, the chapter outlines future directions for chatbot development, emphasizing human-AI collaboration and the importance of ethical, learner-centered design in realizing the full potential of chatbots to transform personalized learning in higher education.