Semantic segmentation is a fundamental topic in computer vision. Several deep learning methods have been proposed for semantic segmentation with outstanding results. However, these models require a lot of densely annotated images. To address this problem, we propose a new algorithm that uses Hy-perGraph Convolutional Networks for Weakly-supervised Semantic Segmentation (HyperGCN-WSS). Our algorithm constructs spatial and k-Nearest Neighbor (k-NN) graphs from the images in the dataset to generate the hypergraphs. Then, we train a specialized HyperGraph Convolutional Network (HyperGCN) architecture using some weak signals. The outputs of the HyperGCN are denominated pseudo-labels, which are later used to train a DeepLab model for semantic segmentation. HyperGCN-WSS is evaluated on the PASCAL VOC 2012 dataset for semantic segmentation, using scribbles or clicks as weak signals. Our algorithm shows competitive performance against previous methods.

This supplement contains seven revised and extended papers selected from CIBB 2018 and CIBB 2019, the 15th and 16th editions of the international conference on Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB is a venue that embraces researchers with different backgrounds, ranging from mathematics to computer science, from materials science to medicine, and from engineering to biology, all interested in the investigation and application of computational intelligence methods to open problems in bioinformatics, biostatistics, systems biology, synthetic biology, and medical informatics.

BACKGROUND: High throughput methods, in biological and biomedical fields, acquire a large number of molecular parameters or omics data by a single experiment. Combining these omics data can significantly increase the capability for recovering fine-tuned structures or reducing the effects of experimental and biological noise in data. RESULTS: In this work we propose a multi-view integration methodology (named FH-Clust) for identifying patient subgroups from different omics information (e.g., Gene Expression, Mirna Expression, Methylation). In particular, hierarchical structures of patient data are obtained in each omic (or view) and finally their topologies are merged by consensus matrix. One of the main aspects of this methodology, is the use of a measure of dissimilarity between sets of observations, by using an appropriate metric. For each view, a dendrogram is obtained by using a hierarchical clustering based on a fuzzy equivalence relation with Łukasiewicz valued fuzzy similarity. Finally, a consensus matrix, that is a representative information of all dendrograms, is formed by combining multiple hierarchical agglomerations by an approach based on transitive consensus matrix construction. Several experiments and comparisons are made on real data (e.g., Glioblastoma, Prostate Cancer) to assess the proposed approach. CONCLUSIONS: Fuzzy logic allows us to introduce more flexible data agglomeration techniques. From the analysis of scientific literature, it appears to be the first time that a model based on fuzzy logic is used for the agglomeration of multi-omic data. The results suggest that FH-Clust provides better prognostic value and clinical significance compared to the analysis of single-omic data alone and it is very competitive with respect to other techniques from literature.

In the era of the Internet of Things (IoT), numerous application domains are emerging for a new generation of networked smart devices capable to process and communicate data over the Internet, for building a new smart world. While some large scale domains are certainly of a special interest, e.g., smart grid, some others small scale applications, e.g., smart home, give any user the chance to build his own IoT system. Thanks to the technological development, it is now possible to use and integrate cheap technologies to monitor the state of our homes. The paper is devoted to the implementation of an inexpensive system to measure the energy consumption of a home electrical appliances. An Arduino board equipped with a proper sensor is connected to the specific appliance one wants to monitor, and a web application running on a web server accessible through any device, i.e., pc, tablet or smartphone, makes it possible the real-time monitoring of the energy consumptions and to query for the historical energy rates. Moreover, a forecasting module based on a Radial Basis Function Neural Network trained, in the first layer, by a rough-fuzzy supervised clustering, provides future energy trends.

MOTIVATION: The huge growth in gene expression data calls for the implementation of automatic tools for data processing and interpretation. RESULTS: We present a new and comprehensive machine learning data mining framework consisting in a non-linear PCA neural network for feature extraction, and probabilistic principal surfaces combined with an agglomerative approach based on Negentropy aimed at clustering gene microarray data. The method, which provides a user-friendly visualization interface, can work on noisy data with missing points and represents an automatic procedure to get, with no a priori assumptions, the number of clusters present in the data. Cell-cycle dataset and a detailed analysis confirm the biological nature of the most significant clusters. AVAILABILITY: The software described here is a subpackage part of the ASTRONEURAL package and is available upon request from the corresponding author. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Bioinformatics systems benefit from the use of data mining strategies to locate interesting and pertinent relationships within massive information. For example, data mining methods can ascertain and summarize the set of genes responding to a certain level of stress in an organism. Even a cursory glance through the literature in journals, reveals the persistent role of data mining in experimental biology. Integrating data mining within the context of experimental investigations is central to bioinformatics software. In this paper we describe the framework of probabilistic principal surfaces, a latent variable model which offers a large variety of appealing visualization capabilities and which can be successfully integrated in the context of microarray analysis. A preprocessing phase consisting of a nonlinear PCA neural network which seems to be very useful to deal with noisy and time dependent nature of microarray data has been added to this framework.

The recent technological advances are producing huge data sets in almost all fields of scientific research, from astronomy to genetics. Although each research field often requires ad-hoc, fine tuned, procedures to properly exploit all the available information inherently present in the data, there is an urgent need for a new generation of general computational theories and tools capable to boost most human activities of data analysis. Here, we propose probabilistic principal surfaces (PPS) as an effective high-D data visualization and clustering tool for data mining applications, emphasizing its flexibility and generality of use in data-rich field. In order to better illustrate the potentialities of the method, we also provide a real world case-study by discussing the use of PPS for the analysis of yeast gene expression levels from microarray chips.

Probabilistic Principal Surfaces is a promising latent variable model which represents a powerful tool to be used in a large range of data mining applications, due to its valuable capabilities in data visualization and classification tasks. In This work we focus our attention on the latter issue, proposing two combining schemes to build an ensemble of Probabilistic Principal Surfaces which is proved to be very effective in classifying very complex artificial and real-world astronomincal data.

We propose a genetic-level clustering methodology able to cluster objects represented by R/sup p/ spaces. The unsupervised cluster algorithm is based on a fuzzy clustering c-means method that searches the best fuzzy partition of the universe assuming that the evaluation of each object respect to some features is unknown, but knowing that it belongs to circular region of R/sup 2/ space.

The main goal of evolutionary computation is to provide a near optimal technique between exploration and exploitation of a search space. This approach is based on a genetic “engine” that operates the search of the optimal solution via biological-based assumptions. Selection of the optimal maintenance interventions activity, that can be tackled with success thanks to an evolutionary approach able to correct the distresses on the road pavement, is a very complex task. This paper presents an experimental architecture that improves the evolutionary aspect with additional benefits deriving from a synergistic combination of other powerful techniques, in particular neural networks and fuzzy logic. The best rules for managing pavement maintenance activities, developed through a genetic selection, are judged by a neural network. By an appropriate introduction of simple and efficient fuzzy identifiers, the features of the distress to treat can be described in an efficient and natural way. We describe the main advantages arising from this hybrid approach discussing the applicability of the method with experimental results. © 2000 John Wiley & Sons, Inc.