1 January 2024 in Journal on Interactive Systems
In an effort to advance Digital Agriculture, this paper provides a comparative assessment of Artificial Neural Networks for intelligent detection of a major biotic stress factors in coffee cultivation. Through a multi-class Computer Vision task, the superior performance of Convolutional Neural Networks, notably the ShuffleNet architecture, was discerned, further substantiated by statistical analyses. This model's performance, akin to state-of-the-art solutions, was achieved with reduced training data and parameter requirements. Robustness was affirmed through external validation using alternative datasets. This contribution directly enhances coffee plantations' quality and supports the development of Edge Computing devices for Agricultural IoT.
18 March 2024 in Journal of Intelligent & Robotic Systems
Computational Thinking has been recognized as an essential skill to be developed in individuals of the 21st Century. Various initiatives worldwide have been proposed to establish the most effective educational strategies and resources to support the development of these skills. With the publication of the Standards for Computing in Basic Education in Brazil (Complement to the National Base Common Curricular), Computer Science is expected to be taught as a fundamental science from Early Childhood Education to High School. In this context, this study presents the results of the students’ learning and the usability evaluation of the ThinkCarpet: an interactive educational robotics artifact built using alternative materials and Arduino, with the purpose of aiding in the development of the concept of algorithms in students from Middle School. Regarding the students’ learning, an average of 93.75% of valid solutions was observed for the algorithms validated through the use of the ThinkCarpet. In contrast, only 62% of valid solutions were identified in activities outside the proposed resource. As for the results of the application of the System Usability Scale (SUS), the results show a score of 83.59, which classifies the ThinkCarpet as excellent in a realistic scenario.
4 March 2024 in Journal of Internet Services and Applications
In state-of-art anomaly detection research, prevailing methodologies predominantly employ Generative Adversarial Networks and Autoencoders for image-based applications. Despite the efficacy demonstrated in the visual domain, there remains a notable dearth of studies showcasing the application of these architectures in anomaly detection within the sound domain. This paper introduces tailored adaptations of cutting-edge architectures for anomaly detection in audio and conducts a comprehensive comparative analysis to substantiate the viability of this novel approach. The evaluation is performed on the DCASE 2020 dataset, encompassing over 180 hours of industrial machinery sound recordings. Our results indicate superior anomaly classification, with an average Area Under the Curve (AUC) of 88.16% and partial AUC of 78.05%, surpassing the performance of established baselines. This study not only extends the applicability of advanced architectures to the audio domain but also establishes their effectiveness in the challenging context of industrial sound anomaly detection.