The transformative capabilities of large language models (LLMs) are reshaping educational assessment and question design in higher education. This study proposes a systematic framework for leveraging LLMs to enhance question-centric tasks: aligning exam questions with course objectives, improving clarity and difficulty, and generating new items guided by learning goals. The research spans four university courses—two theory-focused and two application-focused—covering diverse cognitive levels according to Bloom’s taxonomy. A balanced dataset ensures representation of question categories and structures. Three LLM-based agents—VectorRAG, VectorGraphRAG, and a fine-tuned LLM—are developed and evaluated against a meta-evaluator, supervised by human experts, to assess alignment accuracy and explanation quality. Robust analytical methods, including mixed-effects modeling, yield actionable insights for integrating generative AI into university assessment processes. Beyond exam-specific applications, this methodology provides a foundational approach for the broader adoption of AI in post-secondary education, emphasizing fairness, contextual relevance, and collaboration. The findings offer a comprehensive framework for aligning AI-generated content with learning objectives, detailing effective integration strategies, and addressing challenges such as bias and contextual limitations. Overall, this work underscores the potential of generative AI to enhance educational assessment while identifying pathways for responsible implementation.

This paper presents a proof of the concept cloud based patient monitoring and self-care platform, powered by measurements provided from various smartphone sensors. The Cloud platform provides the infrastructure and computational capacity for calculation of the navigation and motion tracking system, fall detection monitoring, as well as emergency notifications. The navigation system uses the pedometer and fusion of the accelerometer, gyroscope and magnetometer sensors. It aims to estimate precisely the patient’s movement and location. While both navigation and tracking systems can independently determine the incremental movement and indoor localization of the patients, they are fused in order to provide more accurate estimations. The fall detection monitoring is enabled by processing the raw data collected from the smartphone’s accelerometer and gyroscope. Furthermore, the cloud system provides various statistics for the physical activity of the patients, based on measurements from the pedometer. Consequently, this paper proposes a proof of the concept cloud based platform that is scalable and highly responsive, used for real-time monitoring and tracking a large number of patients. It also provides indoor navigation and other self-care features.

Information about the paper titled "LEARNING ANALYTICS - CASE STUDY: SEMANTIC AND SENTIMENT ANALYSES OF STUDENTS FEEDBACK IN HIGHER EDUCATION" at IATED Digital Library