Soundscape Characterization Using Autoencoders and Unsupervised Learning.

Passive acoustic monitoring (PAM) through acoustic recorder units (ARUs) shows promise in detecting early landscape changes linked to functional and structural patterns, including species richness, acoustic diversity, community interactions, and human-induced threats. However, current approaches primarily rely on supervised methods, which require prior knowledge of collected datasets. This reliance poses challenges due to the large volumes of ARU data. In this work, we propose a non-supervised framework using autoencoders to extract soundscape features. We applied this framework to a dataset from Colombian landscapes captured by 31 audiomoth recorders. Our method generates clusters based on autoencoder features and represents cluster information with prototype spectrograms using centroid features and the decoder part of the neural network. Our analysis provides valuable insights into the distribution and temporal patterns of various sound compositions within the study area. By utilizing autoencoders, we identify significant soundscape patterns characterized by recurring and intense sound types across multiple frequency ranges. This comprehensive understanding of the study area's soundscape allows us to pinpoint crucial sound sources and gain deeper insights into its acoustic environment. Our results encourage further exploration of unsupervised algorithms in soundscape analysis as a promising alternative path for understanding and monitoring environmental changes.

Towards Decoding Hepatotoxicity of Approved Drugs through Navigation of Multiverse and Consensus Chemical Spaces.

Drug-induced liver injury (DILI) is the principal reason for failure in developing drug candidates. It is the most common reason to withdraw from the market after a drug has been approved for clinical use. In this context, data from animal models, liver function tests, and chemical properties could complement each other to understand DILI events better and prevent them. Since the chemical space concept improves decision-making drug design related to the prediction of structure-property relationships, side effects, and polypharmacology drug activity (uniquely mentioning the most recent advances), it is an attractive approach to combining different phenomena influencing DILI events (e.g., individual "chemical spaces") and exploring all events simultaneously in an integrated analysis of the DILI-relevant chemical space. However, currently, no systematic methods allow the fusion of a collection of different chemical spaces to collect different types of data on a unique chemical space representation, namely "consensus chemical space." This study is the first report that implements data fusion to consider different criteria simultaneously to facilitate the analysis of DILI-related events. In particular, the study highlights the importance of analyzing together in vitro and chemical data (e.g., topology, bond order, atom types, presence of rings, ring sizes, and aromaticity of compounds encoded on RDKit fingerprints). These properties could be aimed at improving the understanding of DILI events.

Local-Sensitive Connectivity Filter (LS-CF): A Post-Processing Unsupervised Improvement of the Frangi, Hessian and Vesselness Filters for Multimodal Vessel Segmentation.

A retinal vessel analysis is a procedure that can be used as an assessment of risks to the eye. This work proposes an unsupervised multimodal approach that improves the response of the Frangi filter, enabling automatic vessel segmentation. We propose a filter that computes pixel-level vessel continuity while introducing a local tolerance heuristic to fill in vessel discontinuities produced by the Frangi response. This proposal, called the local-sensitive connectivity filter (LS-CF), is compared against a naive connectivity filter to the baseline thresholded Frangi filter response and to the naive connectivity filter response in combination with the morphological closing and to the current approaches in the literature. The proposal was able to achieve competitive results in a variety of multimodal datasets. It was robust enough to outperform all the state-of-the-art approaches in the literature for the OSIRIX angiographic dataset in terms of accuracy and 4 out of 5 works in the case of the IOSTAR dataset while also outperforming several works in the case of the DRIVE and STARE datasets and 6 out of 10 in the CHASE-DB dataset. For the CHASE-DB, it also outperformed all the state-of-the-art unsupervised methods.

Human Activity Recognition Data Analysis: History, Evolutions, and New Trends.

The Assisted Living Environments Research Area-AAL (Ambient Assisted Living), focuses on generating innovative technology, products, and services to assist, medical care and rehabilitation to older adults, to increase the time in which these people can live. independently, whether they suffer from neurodegenerative diseases or some disability. This important area is responsible for the development of activity recognition systems-ARS (Activity Recognition Systems), which is a valuable tool when it comes to identifying the type of activity carried out by older adults, to provide them with assistance. that allows you to carry out your daily activities with complete normality. This article aims to show the review of the literature and the evolution of the different techniques for processing this type of data from supervised, unsupervised, ensembled learning, deep learning, reinforcement learning, transfer learning, and metaheuristics approach applied to this sector of science. health, showing the metrics of recent experiments for researchers in this area of knowledge. As a result of this article, it can be identified that models based on reinforcement or transfer learning constitute a good line of work for the processing and analysis of human recognition activities.

Unsupervised Learning Applied to the Stratification of Preterm Birth Risk in Brazil with Socioeconomic Data.

Preterm birth (PTB) is a phenomenon that brings risks and challenges for the survival of the newborn child. Despite many advances in research, not all the causes of PTB are already clear. It is understood that PTB risk is multi-factorial and can also be associated with socioeconomic factors. Thereby, this article seeks to use unsupervised learning techniques to stratify PTB risk in Brazil using only socioeconomic data. Through the use of datasets made publicly available by the Federal Government of Brazil, a new dataset was generated with municipality-level socioeconomic data and a PTB occurrence rate. This dataset was processed using various unsupervised learning techniques, such as k-means, principal component analysis (PCA), and density-based spatial clustering of applications with noise (DBSCAN). After validation, four clusters with high levels of PTB occurrence were discovered, as well as three with low levels. The clusters with high PTB were comprised mostly of municipalities with lower levels of education, worse quality of public services-such as basic sanitation and garbage collection-and a less white population. The regional distribution of the clusters was also observed, with clusters of high PTB located mostly in the North and Northeast regions of Brazil. The results indicate a positive influence of the quality of life and the offer of public services on the reduction in PTB risk.

PyRAT: An Open-Source Python Library for Animal Behavior Analysis.

Here we developed an open-source Python-based library called Python rodent Analysis and Tracking (PyRAT). Our library analyzes tracking data to classify distinct behaviors, estimate traveled distance, speed and area occupancy. To classify and cluster behaviors, we used two unsupervised algorithms: hierarchical agglomerative clustering and t-distributed stochastic neighbor embedding (t-SNE). Finally, we built algorithms that associate the detected behaviors with synchronized neural data and facilitate the visualization of this association in the pixel space. PyRAT is fully available on GitHub: https://github.com/pyratlib/pyrat.

Using bi-dimensional representations to understand patterns in COVID-19 blood exam data.

Blood tests play an essential role in everyday medicine and are used by doctors in several diagnostic procedures. Moreover, this data is multivariate - and often some diseases, such as COVID-19, could have different symptom manifestations and outcomes. This study proposes a method of extracting useful information from blood tests using UMAP technique - Uniform Manifold Approximation and Projection for Dimension Reduction combined with DBSCAN clustering and statistical approaches. The analysis performed here indicates several clusters of infection prevalence varying between 2%-37%, showing that our procedure is indeed capable of finding different patterns. A possible explanation is that COVID-19 is not just a respiratory infection but a systemic disease with critical hematological implications, primarily on white-cell fractions, as indicated by relevant statistical test p -values in the range of 0.03-0.1. The novel analysis procedure proposed could be adopted in other data-sets of different illnesses to help researchers to discover new patterns of data that could be used in various diseases and contexts.

Sleep Phases in Crayfish: Relationship Between Brain Electrical Activity and Autonomic Variables.

In vertebrates like mammals and birds, two types of sleep have been identified: rapid eye movement and non-rapid eye movement sleep. Each one is associated with specific electroencephalogram patterns and is accompanied by variations in cardiac and respiratory frequencies. Sleep has been demonstrated only in a handful of invertebrates, and evidence for different sleep stages remains elusive. Previous results show that crayfish sleeps while lying on one side on the surface of the water, but it is not known if this animal has sleep phases. Heart rate and respiratory frequency are modified by diverse changes in the crayfish environment during wakefulness, and previously, we showed that variations in these variables are present during sleep despite that there are no autonomic anatomical structures described in this animal. Here, we conducted experiments to search for sleep phases in crayfish and the relationships between sleep and cardiorespiratory activity. We used the wavelet transform, grouping analysis with k-means clustering, and principal component analysis, to analyze brain and cardiorespiratory electrical activity. Our results show that (a) crayfish can sleep lying on one side or when it is motionless and (b) the depth of sleep (measured as the power of electroencephalographic activity) changes over time and is accompanied by oscillations in cardiorespiratory signal amplitude and power. Finally, we propose that in crayfish there are at least three phases of sleep.

A Computational Theory for the Emergence of Grammatical Categories in Cortical Dynamics.

A general agreement in psycholinguistics claims that syntax and meaning are unified precisely and very quickly during online sentence processing. Although several theories have advanced arguments regarding the neurocomputational bases of this phenomenon, we argue that these theories could potentially benefit by including neurophysiological data concerning cortical dynamics constraints in brain tissue. In addition, some theories promote the integration of complex optimization methods in neural tissue. In this paper we attempt to fill these gaps introducing a computational model inspired in the dynamics of cortical tissue. In our modeling approach, proximal afferent dendrites produce stochastic cellular activations, while distal dendritic branches-on the other hand-contribute independently to somatic depolarization by means of dendritic spikes, and finally, prediction failures produce massive firing events preventing formation of sparse distributed representations. The model presented in this paper combines semantic and coarse-grained syntactic constraints for each word in a sentence context until grammatically related word function discrimination emerges spontaneously by the sole correlation of lexical information from different sources without applying complex optimization methods. By means of support vector machine techniques, we show that the sparse activation features returned by our approach are well suited-bootstrapping from the features returned by Word Embedding mechanisms-to accomplish grammatical function classification of individual words in a sentence. In this way we develop a biologically guided computational explanation for linguistically relevant unification processes in cortex which connects psycholinguistics to neurobiological accounts of language. We also claim that the computational hypotheses established in this research could foster future work on biologically-inspired learning algorithms for natural language processing applications.

Muscle fatigue analysis during dynamic contractions based on biomechanical features and Permutation Entropy.

Muscle fatigue is an important field of study in sports medicine and occupational health. Several studies in the literature have proposed methods for predicting muscle fatigue in isometric con-tractions using three states of muscular fatigue: Non-Fatigue, Transition-to-Fatigue, and Fatigue. For this, several features in time, spectral and time-frequency domains have been used, with good performance results; however, when they are applied to dynamic contractions the performance decreases. In this paper, we propose an approach for analyzing muscle fatigue during dynamic contractions based on time and spectral domain features, Permutation Entropy (PE) and biomechanical features. We established a protocol for fatiguing the deltoid muscle and acquiring surface electromiography (sEMG) and biomechanical signals. Subsequently, we segmented the sEMG and biomechanical signals of every contraction. In order to label the contraction, we computed some features from biomechanical signals and evaluated their correlation with fatigue progression, and the most correlated variables were used to label the contraction using hierarchical clustering with Ward's linkage. Finally, we analyzed the discriminant capacity of sEMG features using ANOVA and ROC analysis. Our results show that the biomechanical features obtained from angle and angular velocity are related to fatigue progression, the analysis of sEMG signals shows that PE could distinguish Non-Fatigue, Transition-to-Fatigue and Fatigue more effectively than classical sEMG features of muscle fatigue such as Median Frequency.

CuMiDa: An Extensively Curated Microarray Database for Benchmarking and Testing of Machine Learning Approaches in Cancer Research.

The employment of machine learning (ML) approaches to extract gene expression information from microarray studies has increased in the past years, specially on cancer-related works. However, despite this continuous interest in applying ML in cancer biomedical research, there are no curated repositories focused only on providing quality data sets exclusively for benchmarking and testing of such techniques for cancer research. Thus, in this work, we present the Curated Microarray Database (CuMiDa), a database composed of 78 handpicked microarray data sets for Homo sapiens that were carefully examined from more than 30,000 microarray experiments from the Gene Expression Omnibus using a rigorous filtering criteria. All data sets were individually submitted to background correction, normalization, sample quality analysis and were manually edited to eliminate erroneous probes. All data sets were tested using principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) analyses to observe sample division and were additionally tested using various ML approaches to provide a base accuracy for the major techniques employed for microarray data sets. CuMiDa is a database created solely for benchmarking and testing of ML approaches applied to cancer research.

Unsupervised visual discrimination learning of complex stimuli: Accuracy, bias and generalization.

Through same-different judgements, we can discriminate an immense variety of stimuli and consequently, they are critical in our everyday interaction with the environment. The quality of the judgements depends on familiarity with stimuli. A way to improve the discrimination is through learning, but to this day, we lack direct evidence of how learning shapes the same-different judgments with complex stimuli. We studied unsupervised visual discrimination learning in 42 participants, as they performed same-different judgments with two types of unfamiliar complex stimuli in the absence of labeling or individuation. Across nine daily training sessions with equiprobable same and different stimuli pairs, participants increased the sensitivity and the criterion by reducing the errors with both same and different pairs. With practice, there was a superior performance for different pairs and a bias for different response. To evaluate the process underlying this bias, we manipulated the proportion of same and different pairs, which resulted in an additional proportion-induced bias, suggesting that the bias observed with equal proportions was a stimulus processing bias. Overall, these results suggest that unsupervised discrimination learning occurs through changes in the stimulus processing that increase the sensory evidence and/or the precision of the working memory. Finally, the acquired discrimination ability was fully transferred to novel exemplars of the practiced stimuli category, in agreement with the acquisition of a category specific perceptual expertise.

Graph-based Clustering of miRNA Sequences.

AIMS: The many miRNAs discovered so far have been divided into biologically representative families, aiming at organizing and systematizing their study so to promote, mainly, a better understanding of their functionalities. Clustering miRNA sequences can corroborate the family-based organizations as well as helping to explore sequences belonging to the same cluster as potentially having similar biological functions. OBSERVATIONS: Considering that members of the same miRNA family tend to biologically function in similar ways, a well-structured family can help detecting miRNA functions which have not been associated yet with any existing family. METHODS: The work described in this paper empirically investigates the suitability of organizing miRNAs as families, using a clustering algorithm based on a particular type of graph i.e., minimal spanning tree (MST), for clustering miRNA sequences. Seven miRNA families stored in the online miRBase database have been used as input to the MST-based clustering algorithm and clustering results have been compared to assess the suitability of identirying them. RESULTS: The motivations for the experiments were to identify refinements in miRNA family organizations that could be pursued and, also, investigate how the chosen graph-based clustering algorithm would perform in miRNA related domains. CONCLUSION: Interesting and useful results, particularly related to detecting information based on the visualization of the final induced graphs, and their induced connected components (clusters), are presented and discussed. Particularly, experiments results suggested the possibility of refining some miRNA families by grouping some of their miRNAs as sub-families.

A Marked Point Process Framework for Extracellular Electrical Potentials.

Neuromodulations are an important component of extracellular electrical potentials (EEP), such as the Electroencephalogram (EEG), Electrocorticogram (ECoG) and Local Field Potentials (LFP). This spatially temporal organized multi-frequency transient (phasic) activity reflects the multiscale spatiotemporal synchronization of neuronal populations in response to external stimuli or internal physiological processes. We propose a novel generative statistical model of a single EEP channel, where the collected signal is regarded as the noisy addition of reoccurring, multi-frequency phasic events over time. One of the main advantages of the proposed framework is the exceptional temporal resolution in the time location of the EEP phasic events, e.g., up to the sampling period utilized in the data collection. Therefore, this allows for the first time a description of neuromodulation in EEPs as a Marked Point Process (MPP), represented by their amplitude, center frequency, duration, and time of occurrence. The generative model for the multi-frequency phasic events exploits sparseness and involves a shift-invariant implementation of the clustering technique known as k-means. The cost function incorporates a robust estimation component based on correntropy to mitigate the outliers caused by the inherent noise in the EEP. Lastly, the background EEP activity is explicitly modeled as the non-sparse component of the collected signal to further improve the delineation of the multi-frequency phasic events in time. The framework is validated using two publicly available datasets: the DREAMS sleep spindles database and one of the Brain-Computer Interface (BCI) competition datasets. The results achieve benchmark performance and provide novel quantitative descriptions based on power, event rates and timing in order to assess behavioral correlates beyond the classical power spectrum-based analysis. This opens the possibility for a unifying point process framework of multiscale brain activity where simultaneous recordings of EEP and the underlying single neuron spike activity can be integrated and regarded as marked and simple point processes, respectively.

Application of self-organising maps towards segmentation of soybean samples by determination of inorganic compounds content.

BACKGROUND: In this study, 20 samples of soybean, both transgenic and conventional cultivars, which were planted in two different regions, Londrina and Ponta Grossa, both located at Paraná, Brazil, were analysed. In order to verify whether the inorganic compound levels in soybeans varied with the region of planting, K, P, Ca, Mg, S, Zn, Mn, Fe, Cu and B contents were analysed by an artificial neural network self-organising map. RESULTS: It was observed that with a topology 10 × 10, 8000 epochs, initial learning rate of 0.1 and initial neighbourhood ratio of 4.5, the network was able to differentiate samples according to region of origin. Among all of the variables analysed by the artificial neural network, the elements Zn, Ca and Mn were those which most contributed to the classification of the samples. CONCLUSION: The results indicated that samples planted in these two regions differ in their mineral content; however, conventional and transgenic samples grown in the same region show no difference in mineral contents in the grain.

Detecting abnormal vehicular dynamics at intersections based on an unsupervised learning approach and a stochastic model.

This investigation demonstrates an unsupervised approach for modeling traffic flow and detecting abnormal vehicle behaviors at intersections. In the first stage, the approach reveals and records the different states of the system. These states are the result of coding and grouping the historical motion of vehicles as long binary strings. In the second stage, using sequences of the recorded states, a stochastic graph model based on a Markovian approach is built. A behavior is labeled abnormal when current motion pattern cannot be recognized as any state of the system or a particular sequence of states cannot be parsed with the stochastic model. The approach is tested with several sequences of images acquired from a vehicular intersection where the traffic flow and duration used in connection with the traffic lights are continuously changed throughout the day. Finally, the low complexity and the flexibility of the approach make it reliable for use in real time systems.