How validation methodology influences human activity recognition mobile systems

H Bragança, JG Colonna, HABF Oliveira, E Souto - Sensors, 2022‏ - mdpi.com
In this article, we introduce explainable methods to understand how Human Activity
Recognition (HAR) mobile systems perform based on the chosen validation strategies. Our …

Bioacoustic signal classification in continuous recordings: Syllable-segmentation vs sliding-window

J **e, K Hu, M Zhu, Y Guo - Expert Systems with Applications, 2020‏ - Elsevier
Frog population has been experiencing rapid decreases worldwide, which is regarded as
one of the most critical threats to the global biodiversity. Therefore, large volumes of frog …

[HTML][HTML] From theory to practice: A data quality framework for classification tasks

DC Corrales, A Ledezma, JC Corrales - Symmetry, 2018‏ - mdpi.com
The data preprocessing is an essential step in knowledge discovery projects. The experts
affirm that preprocessing tasks take between 50% to 70% of the total time of the knowledge …

Pattern analysis based acoustic signal processing: a survey of the state-of-art

J Chaki - International Journal of Speech Technology, 2021‏ - Springer
Audio signal processing is the most challenging field in the current era for an analysis of an
audio signal. Audio signal classification (ASC) comprises of generating appropriate features …

Easy variational inference for categorical models via an independent binary approximation

MT Wojnowicz, S Aeron, EL Miller… - … on Machine Learning, 2022‏ - proceedings.mlr.press
We pursue tractable Bayesian analysis of generalized linear models (GLMs) for categorical
data. GLMs have been difficult to scale to more than a few dozen categories due to non …

Mutual singular spectrum analysis for bioacoustics classification

BB Gatto, JG Colonna, EM dos Santos… - 2017 IEEE 27th …, 2017‏ - ieeexplore.ieee.org
Bioacoustics signals classification is an important instrument used in environmental
monitoring as it gives the means to efficiently acquire information from the areas, which most …

A comparison of hierarchical multi-output recognition approaches for anuran classification

JG Colonna, J Gama, EF Nakamura - Machine Learning, 2018‏ - Springer
In bioacoustic recognition approaches, a “flat” classifier is usually trained to recognize
several species of anurans, where the number of classes is equal to the number of species …

Signal conditioning for learning in the wild

A Borthakur, TA Cleland - Proceedings of the 7th Annual Neuro-inspired …, 2019‏ - dl.acm.org
The mammalian olfactory system learns rapidly from very few examples, presented in
unpredictable online sequences, and then recognizes these learned odors under conditions …

Unsupervised selection of the singular spectrum components based on information theory for bioacoustic signal filtering

JG Colonna, EF Nakamura - Digital Signal Processing, 2018‏ - Elsevier
In this work, we present a comprehensive study of Singular Spectrum Analysis (SSA)
applied to bioacoustics signal enhancement. The SSA method decomposes the signal into …

Discriminative singular spectrum classifier with applications on bioacoustic signal recognition

BB Gatto, JG Colonna, EM dos Santos… - Digital Signal …, 2023‏ - Elsevier
Automatic analysis of bioacoustic signals is a fundamental tool to evaluate the vitality of our
planet. Frogs and bees, for instance, may act like biological sensors providing information …