arXiv subjects

Ivens Portugal

Publications and source records attributed to Ivens Portugal.

8 recordsLinked to original sources

arXiv2026

CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening

This paper presents CPEMH, an agentic framework designed to evaluate prompt-driven behavior in foundation-model systems operating on transcript-based datasets for mental-health screening. CPEMH serves as an engineering methodology for behavioral assurance in large-scale language systems, introducing an orchestrated architecture that autonomously performs the design, evaluation, and selection of prompt strategies, enabling systematic control of behavioral variability across contexts. Its modular agentic design, combining orchestrator, inference, and evaluation agents, ensures traceability, reproducibility, and robustness throughout the prompting lifecycle. A case study on automated depression screening from interview transcripts demonstrates the framework's capacity to stabilize and audit foundation-model behavior in conversational and clinically sensitive domains. Lessons learned emphasize the role of modular orchestration in behavioral assurance, the prioritization of stability over architectural complexity, and the integration of F1, bias, and robustness as core acceptance criteria.

cs.AI↗

arXiv2024

Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT

This study evaluates fine-tuning strategies for text classification using the DistilBERT model, specifically the distilbert-base-uncased-finetuned-sst-2-english variant. Through structured experiments, we examine the influence of hyperparameters such as learning rate, batch size, and epochs on accuracy, F1-score, and loss. Polynomial regression analyses capture foundational and incremental impacts of these hyperparameters, focusing on fine-tuning adjustments relative to a baseline model. Results reveal variability in metrics due to hyperparameter configurations, showing trade-offs among performance metrics. For example, a higher learning rate reduces loss in relative analysis (p=0.027) but challenges accuracy improvements. Meanwhile, batch size significantly impacts accuracy and F1-score in absolute regression (p=0.028 and p=0.005) but has limited influence on loss optimization (p=0.170). The interaction between epochs and batch size maximizes F1-score (p=0.001), underscoring the importance of hyperparameter interplay. These findings highlight the need for fine-tuning strategies addressing non-linear hyperparameter interactions to balance performance across metrics. Such variability and metric trade-offs are relevant for tasks beyond text classification, including NLP and computer vision. This analysis informs fine-tuning strategies for large language models and promotes adaptive designs for broader model applicability.

cs.CL↗

arXiv2019

Spatial-Temporal Cluster Relations -- A Foundation for Trajectory Cluster Lifetime Analysis

Spatial-temporal data, that is information about objects that exist at a particular location and time period, are rich in value and, as a consequence, the target of so many initiative efforts. Clustering approaches aim at grouping datapoints based on similar properties for classification tasks. These approaches have been widely used in domains such as human mobility, ecology, health and astronomy. However, clustering approaches typically address only the static nature of a cluster, and do not take into consideration its dynamic aspects. A desirable approach needs to investigate relations between dynamic clusters and their elements that can be used to derive new insights about what happened to the clusters during their lifetimes. A fundamental step towards this goal is to provide a formal definition of spatial-temporal cluster relations. This report introduces, describes, and formalizes 14 novel spatial-temporal cluster relations that may occur during the existence of a cluster and involve both trajectory-cluster membership conditions and cluster-cluster comparisons. We evaluate the proposed relations with a discussion on how they are able to interpret complex cases that are difficult to be distinguished without a formal relation specification. We conclude the report by summarizing our results and describing avenues for further research.

cs.DB↗

arXiv2018

Cluster Lifecycle Analysis: Challenges, Techniques, and Framework

Novel forms of data analysis methods have emerged as a significant research direction in the transportation domain. These methods can potentially help to improve our understanding of the dynamic flows of vehicles, people, and goods. Understanding these dynamics has economic and social consequences, which can improve the quality of life locally or worldwide. Aiming at this objective, a significant amount of research has focused on clustering moving objects to address problems in many domains, including the transportation, health, and environment. However, previous research has not investigated the lifecycle of a cluster, including cluster genesis, existence, and disappearance. The representation and analysis of cluster lifecycles can create novel avenues for research, result in new insights for analyses, and allow unique forms of prediction. This technical report focuses on studying the lifecycle of clusters by investigating the relations that a cluster has with moving elements and other clusters. This technical report also proposes a big data framework that manages the identification and processing of a cluster lifecycle. The ongoing research approach will lead to new ways to perform cluster analysis and advance the state of the art by leading to new insights related to cluster lifecycle. These results can have a significant impact on transport industry data science applications in a wide variety of areas, including congestion management, resource optimization, and hotspot management.

cs.CY↗

arXiv2017

Developing a Spatial-Temporal Contextual and Semantic Trajectory Clustering Framework

This paper reports on ongoing research investigating more expressive approaches to spatial-temporal trajectory clustering. Spatial-temporal data is increasingly becoming universal as a result of widespread use of GPS and mobile devices, which makes mining and predictive analyses based on trajectories a critical activity in many domains. Trajectory analysis methods based on clustering techniques heavily often rely on a similarity definition to properly provide insights. However, although trajectories are currently described in terms of its two dimensions (space and time), their representation is limited in that it is not expressive enough to capture, in a combined way, the structure of space and time as well as the contextual and semantic trajectory properties. Moreover, the massive amounts of available trajectory data make trajectory mining and analyses very challenging. In this paper, we briefly discuss (i) an improved trajectory representation that takes into consideration space-time structures, context and semantic properties of trajectories; (ii) new forms of relations between the dimensions of a pair of trajectories; and (iii) big data approaches that can be used to develop a novel spatial-temporal clustering framework.

cs.DB↗

arXiv2016

A Survey on Domain-Specific Languages for Machine Learning in Big Data

The amount of data generated in the modern society is increasing rapidly. New problems and novel approaches of data capture, storage, analysis and visualization are responsible for the emergence of the Big Data research field. Machine Learning algorithms can be used in Big Data to make better and more accurate inferences. However, because of the challenges Big Data imposes, these algorithms need to be adapted and optimized to specific applications. One important decision made by software engineers is the choice of the language that is used in the implementation of these algorithms. Therefore, this literature survey identifies and describes domain-specific languages and frameworks used for Machine Learning in Big Data. By doing this, software engineers can then make more informed choices and beginners have an overview of the main languages used in this domain.

cs.SE↗

arXiv2016

Requirements Engineering for General Recommender Systems

In requirements engineering for recommender systems, software engineers must identify the data that drives the recommendations. This is a labor-intensive task, which is error-prone and expensive. One possible solution to this problem is the adoption of automatic recommender system development approach based on a general recommender framework. One step towards the creation of such a framework is to determine the type of data used in recommender systems. In this paper, a systematic review has been conducted to identify the type of user and recommendation data items needed by a general recommender system. A user and item model is proposed, and some considerations about algorithm specific parameters are explained. A further goal is to study the impact of the fields of big data and Internet of things on the development of recommender systems.

cs.SE↗

arXiv2016

The Use of Machine Learning Algorithms in Recommender Systems: A Systematic Review

Recommender systems use algorithms to provide users with product or service recommendations. Recently, these systems have been using machine learning algorithms from the field of artificial intelligence. However, choosing a suitable machine learning algorithm for a recommender system is difficult because of the number of algorithms described in the literature. Researchers and practitioners developing recommender systems are left with little information about the current approaches in algorithm usage. Moreover, the development of a recommender system using a machine learning algorithm often has problems and open questions that must be evaluated, so software engineers know where to focus research efforts. This paper presents a systematic review of the literature that analyzes the use of machine learning algorithms in recommender systems and identifies research opportunities for software engineering research. The study concludes that Bayesian and decision tree algorithms are widely used in recommender systems because of their relative simplicity, and that requirement and design phases of recommender system development appear to offer opportunities for further research.

cs.SE↗