This study explores the integration of Augmented Intelligence (AuI) in Intelligent Tutoring Systems (ITS) to address challenges in Artificial Intelligence in Education (AIED), including teacher involvement, AI reliability, and resource accessibility. We present MathAIde, an ITS that uses computer vision and AI to correct mathematics exercises from student work photos and provide feedback. The system was designed through a collaborative process involving brainstorming with teachers, high-fidelity prototyping, A/B testing, and a real-world case study. Findings emphasize the importance of a teacher-centered, user-driven approach, where AI suggests remediation alternatives while teachers retain decision-making. Results highlight efficiency, usability, and adoption potential in classroom contexts, particularly in resource-limited environments. The study contributes practical insights into designing ITSs that balance user needs and technological feasibility, while advancing AIED research by demonstrating the effectiveness of a mixed-methods, user-centered approach to implementing AuI in educational technologies.

Lung cancer has the highest mortality rate among all cancer types, affecting both men and women. It is estimated that lung cancer accounts for 21 % of cancer deaths in each gender worldwide. In Brazil, lung cancer is the third most common type of cancer among men and the fourth most common among women. This alarming statistic highlights the significant impact of lung cancer on overall cancer mortality, underscoring the urgent need for effective prevention, early detection, and treatment strategies to combat this disease. The Lung-RADS is a standardized classification system for lung nodules detected in imaging exams and assesses the risk of malignancy (cancer) in these nodules to guide subsequent management decisions. In this context, the main goal of this work was to evaluate the effectiveness of using question-answering natural language processing using LLMs to extract lung nodule characteristics from Portuguese chest CT reports for automated Lung-RADS classification. Our most effective model was Llama 3.3708, and this model achieved a weighted F1 score of 84.77 %. Our findings underscore the potential of LLMs to support radiologists in accurately categorizing lung nodules according to Lung-RADS criteria, thereby simplifying the diagnostic process.

Lung cancer has the highest mortality rate among all cancer types for both males and females. It is estimated that lung cancer accounts for 21% of cancer deaths in each gender. This alarming statistic highlights the significant impact of lung cancer on overall cancer mortality, underscoring the urgent need for effective prevention, early detection, and treatment strategies to combat this disease. Lung cancer screening (LCS) is a process that involves carefully selecting high-risk individuals, primarily current or former heavy smokers. It includes annual low-dose computed tomography scans and meticulous interpretation of results followed by appropriate follow-up care. Adherence to LCS follow-up is essential for maximizing the life-saving benefits of this preventive measure. Multiple professional societies, such as the American College of Radiology (ACR) and Fleischner Society, have published guidelines for managing patients with pulmonary nodules. Lung CT Screening Reporting & Data System is a quality assurance tool designed to standardize the reporting of lung cancer screening CT scans and provide consistent management recommendations. In this context, this work aims to evaluate whether large language models (LLM) could accurately identify and extract lung nodules' characteristics from unstructured chest CT reports in the Portuguese, based on the Lung-RADS classification system. This work assessed the effectiveness of three LLMs: Gemini, GPT-4-o, Llama-3 70B, and a BERT model BioBERTpt. Our findings indicate that LLMs, especially GPT-4-o, have significant potential in automating the extraction of lung nodule characteristics for Lung-RADS classification, which could aid radiologists in their work. Notably, GPT-4-o with few-shot learning using Prompt 4 emerged as the best model, achieving an F1-score of 0.89. Our results highlight the potential of LLMs to assist radiologists in accurately classifying lung nodules according to the Lung-RADS criteria, streamlining the diagnostic process.

Cancer represents a significant public health challenge. In 2023, it is projected that cancer will cause the loss of thousands of lives in the United States alone. Lung cancer is the second most commonly diagnosed cancer globally. It represents the deadliest form of malignant neoplasm, resulting in around 1.8 million fatalities in 2020. Chest computed tomography has found extensive application in the assessment of lung cancer, serving as a pivotal tool for non-invasive in vivo initial diagnosis. The utilization of guidelines within screening programs carries substantial significance as it seeks to reduce the requirement for excessive follow-up examinations. The Lung-RADS is one of these guidelines used for screening and follow-up of suspected Lung lesions. It introduces a classification of lung lesions as numbered categories according to their characteristics and degree of suspicion of malignancy. In this context, the main objective of this work is to assess the effectiveness of three Named Entity Recognition (NER) techniques, including CNN, BiLSTM and BERT variants to extract characteristics of pulmonary nodules in chest CT reports in Portuguese idiom and calculate the probability of malignancy index using the Lung-RADS guideline. Our top-performing model was BiLSTM-CRF, and this model achieved an average precision of 96%, an average recall of 88%, and an average f1-score of 90%. This research contributes to advancing NLP applications in the healthcare domain, specifically for Portuguese language radiology reports and demonstrates the potential for automated information extraction to enhance the accuracy and efficiency of lung cancer diagnosis and management.

Novelty detection is a binary task aimed at identifying whether a test sample is novel or unusual compared to a previously observed training set. A typical approach is to consider distance as a criterion to detect such novelties. However, most previous work does not focus on finding an optimum distance for each particular problem. In this paper, we propose to detect novelties by exploiting non-linear distances learned from multi-class training data. For this purpose, we adopt a kernelization technique jointly with the Large Margin Nearest Neighbor (LMNN) metric learning algorithm. The optimum distance tries to keep each known class' instances together while pushing instances from different known classes to remain reasonably distant. We propose a variant of the K-Nearest Neighbors (KNN) classifier that employs the learned distance to detect novelties. Besides, we use the learned distance to perform multi-class classification. We show quantitative and qualitative experiments conducted on synthetic and real data sets, revealing that the learned metrics are effective in improving novelty detection compared to other metrics. Our method also outperforms previous work regularly used for novelty detection.

We present a discriminative key pose-based approach for moves recognition and segmentation of training sequences for high performance sports. Compared to daily human gestures, moves in high performance sports are faster and have low inter-class variability, which produce noisy features and ambiguity. Our approach combines a robust filtering strategy to select frames composed of discriminative poses (key poses) and the discriminative Latent-Dynamic Conditional Random Fields (LDCRF) model to predict a label for each frame from the training sequence. We evaluate our approach on unsegmented sequences of Taekwondo training. Experimental results indicate that our methodology outperforms the Decision Forests method in terms of efficiency and accuracy. Our average recognition rate was equal to 74.72% while Decision Forests achieves 58.29%. The experiments also show that our approach was able to recognize and segment high speed moves like roundhouse kicks, which can reach peak linear speeds up to 26 m/s.

Abstract The definition of a good view of a 3D scene is highly subjective and strongly depends on both the scene content and the 3D application. Usually, camera placement is performed directly by the user, and that task may be laborious. Existing automatic virtual cameras guide the user by optimizing a single rule, e.g. maximizing the visible silhouette or the projected area. However, the use of a static pre‐defined rule may fail in respecting the user's subjective understanding of the scene. This work introduces intelligent design galleries, a learning approach for subjective problems such as the camera placement. The interaction of the user with a design gallery teaches a statistical learning machine. The trained machine can then imitate the user, either by pre‐selecting good views or by automatically placing the camera. The learning process relies on a Support Vector Machines for classifying views from a collection of descriptors, ranging from 2D image quality to 3D features visibility. Experiments of the automatic camera placement demonstrate that the proposed technique is efficient and handles scenes with occlusion and high depth complexities. This work also includes user validations of the intelligent gallery interface.