Ricardo Suyama

Marcos Lima Romero, Ricardo Suyama

The recent development of Agentic AI systems, empowered by autonomous large language models (LLMs) agents with planning and tool-usage capabilities, enables new possibilities for the evolution of industrial automation and reduces the complexity introduced by Industry 4.0. This work proposes a conceptual framework that integrates Agentic AI with the intent-based paradigm, originally developed in network research, to simplify human-machine interaction (HMI) and better align automation systems with the human-centric, sustainable, and resilient principles of Industry 5.0. Based on the intent-based processing, the framework allows human operators to express high-level business or operational goals in natural language, which are decomposed into actionable components. These intents are broken into expectations, conditions, targets, context, and information that guide sub-agents equipped with specialized tools to execute domain-specific tasks. A proof of concept was implemented using the CMAPSS dataset and Google Agent Developer Kit (ADK), demonstrating the feasibility of intent decomposition, agent orchestration, and autonomous decision-making in predictive maintenance scenarios. The results confirm the potential of this approach to reduce technical barriers and enable scalable, intent-driven automation, despite data quality and explainability concerns.

Pedro Ivo da Cruz, Dimitri Silva, Tito Spadini et al.

Massive multiple-input multiple-output (MMIMO) is essential to modern wireless communication systems, like 5G and 6G, but it is vulnerable to active eavesdropping attacks. One type of such attack is the pilot contamination attack (PCA), where a malicious user copies pilot signals from an authentic user during uplink, intentionally interfering with the base station's (BS) channel estimation accuracy. In this work, we propose to use a Decision Tree (DT) algorithm for PCA detection at the BS in a multi-user system. We present a methodology to generate training data for the DT classifier and select the best DT according to their depth. Then, we simulate different scenarios that could be encountered in practice and compare the DT to a classical technique based on likelihood ratio testing (LRT) submitted to the same scenarios. The results revealed that a DT with only one level of depth is sufficient to outperform the LRT. The DT shows a good performance regarding the probability of detection in noisy scenarios and when the malicious user transmits with low power, in which case the LRT fails to detect the PCA. We also show that the reason for the good performance of the DT is its ability to compute a threshold that separates PCA data from non-PCA data better than the LRT's threshold. Moreover, the DT does not necessitate prior knowledge of noise power or assumptions regarding the signal power of malicious users, prerequisites typically essential for LRT and other hypothesis testing methodologies.

Marcos Lima Romero, Ricardo Suyama

Data has become a critical asset in the digital economy, yet it remains underutilized by Mobile Network Operators (MNOs), unlike Over-the-Top (OTT) players that lead global market valuations. To move beyond the commoditization of connectivity and deliver greater value to customers, data analytics emerges as a strategic enabler. Using data efficiently is essential for unlocking new service opportunities, optimizing operational efficiency, and mitigating operational and business risks. Since Release 15, the 3rd Generation Partnership Project (3GPP) has introduced the Network Data Analytics Function (NWDAF) to provide powerful insights and predictions using data collected across mobile networks, supporting both user-centric and network-oriented use cases. However, academic research has largely focused on a limited set of methods and use cases, driven by the availability of datasets, restricting broader exploration. This study analyzes trends and gaps in more than 70 articles and proposes two novel use cases to promote the adoption of NWDAF and explore its potential for monetization.

Roberto Gutierrez Beraldo, Ricardo Suyama

In this book, written in Portuguese, we discuss what ill-posed problems are and how the regularization method is used to solve them. In the form of questions and answers, we reflect on the origins and future of regularization, relating the similarities and differences of its meaning in different areas, including inverse problems, statistics, machine learning, and deep learning.

Renata Pelissari, Ricardo Suyama, Leonardo Tomazeli Duarte et al.

How can a National Artificial Intelligence Strategy be effectively monitored? To address this question, we propose a methodology consisting of two key components. First, it involves identifying relevant indicators within national AI strategies. Second, it assesses the alignment between these indicators and the strategic actions of a specific government's AI strategy, allowing for a critical evaluation of its monitoring measures. Moreover, identifying these indicators helps assess the overall quality of the strategy's structure. A lack of alignment between strategic actions and the identified indicators may reveal gaps or blind spots in the strategy. This methodology is demonstrated using the Brazilian AI strategy as a case study.

Tito Spadini, Kenji Nose-Filho, Ricardo Suyama

This study focuses on Intelligent Fault Diagnosis (IFD) in rotating machinery utilizing a single microphone and a data-driven methodology, effectively diagnosing 42 classes of fault types and severities. The research leverages sound data from the imbalanced MaFaulDa dataset, aiming to strike a balance between high performance and low resource consumption. The testing phase encompassed a variety of configurations, including sampling, quantization, signal normalization, silence removal, Wiener filtering, data scaling, windowing, augmentation, and classifier tuning using XGBoost. Through the analysis of time, frequency, mel-frequency, and statistical features, we achieved an impressive accuracy of 99.54% and an F-Beta score of 99.52% with just 6 boosting trees at an 8 kHz, 8-bit configuration. Moreover, when utilizing only MFCCs along with their first- and second-order deltas, we recorded an accuracy of 97.83% and an F-Beta score of 97.67%. Lastly, by implementing a greedy wrapper approach, we obtained a remarkable accuracy of 96.82% and an F-Beta score of 98.86% using 50 selected features, nearly all of which were first- and second-order deltas of the MFCCs.

Dimitri Leandro de Oliveira Silva, Tito Spadini, Ricardo Suyama

The work assessed seven classical classifiers and two beamforming algorithms for detecting surveillance sound events. The tests included the use of AWGN with -10 dB to 30 dB SNR. Data Augmentation was also employed to improve algorithms' performance. The results showed that the combination of SVM and Delay-and-Sum (DaS) scored the best accuracy (up to 86.0\%), but had high computational cost ($\approx $ 402 ms), mainly due to DaS. The use of SGD also seems to be a good alternative since it has achieved good accuracy either (up to 85.3\%), but with quicker processing time ($\approx$ 165 ms).

Tito Spadini, Dimitri Leandro de Oliveira Silva, Ricardo Suyama

Due to the growing demand for improving surveillance capabilities in smart cities, systems need to be developed to provide better monitoring capabilities to competent authorities, agencies responsible for strategic resource management, and emergency call centers. This work assumes that, as a complementary monitoring solution, the use of a system capable of detecting the occurrence of sound events, performing the Sound Events Recognition (SER) task, is highly convenient. In order to contribute to the classification of such events, this paper explored several classifiers over the SESA dataset, composed of audios of three hazard classes (gunshots, explosions, and sirens) and a class of casual sounds that could be misinterpreted as some of the other sounds. The best result was obtained by SGD, with an accuracy of 72.13% with 6.81 ms classification time, reinforcing the viability of such an approach.

Tito Spadini, Ricardo Suyama

Speech enhancement is a crucial task for several applications. Among the most explored techniques are the Wiener filter and the LogMMSE, but approaches exploring deep learning adapted to this task, such as SEGAN, have presented relevant results. This study compared the performance of the mentioned techniques in 85 noise conditions regarding quality, intelligibility, and distortion; and concluded that classical techniques continue to exhibit superior results for most scenarios, but, in severe noise scenarios, SEGAN performed better and with lower variance.