Maurizio Fiasché

A quantum-inspired evolutionary algorithm for optimization numerical problems

This paper proposes a novel type of quantum-inspired evolutionary algorithm (QiEA) for numerical optimization inspired by the multiple universes principle of quantum computing, which is based on the concept and principles of quantum computing, such as a quantum bit and superposition of states. Numerical optimization problems are an important field of research with several applications in several areas: industrial plant optimization, data mining and many others, and although being successfully used for solving several optimization problems, evolutionary algorithms still present issues that can reduce their performances when faced with task where the evaluation function is computationally intensive. In order to address those issues the QiEA represent the most recent advance in the field of evolutionary computation. This work present some application about combinatorial and numerical optimization problems.

Constructing robust liquid state machines to process highly variable data streams

In this paper, we propose a mechanism to effectively control the overall neural activity in the reservoir of a Liquid State Machine (LSM) in order to achieve both a high sensitivity of the reservoir to weak stimuli as well as an improved resistance to over-stimulation for strong inputs. The idea is to employ a mechanism that dynamically changes the firing threshold of a neuron in dependence of its spike activity. We experimentally demonstrate that reservoirs employing this neural model significantly increase their separation capabilities. We also investigate the role of dynamic and static synapses in this context. The obtained results may be very valuable for LSM based real-world application in which the input signal is often highly variable causing problems of either too little or too much network activity.

Incremental – Adaptive – Knowledge Based – Learning for Informative Rules Extraction in Classification Analysis of aGvHD

Acute graft-versus-host disease (aGvHD) is a serious systemic complication of allogeneic hematopoietic stem cell transplantation (HSCT) that occurs when alloreactive donor-derived T cells recognize host-recipient antigens as foreign. The early events leading to GvHD seem to occur very soon, presumably within hours from the graft infusion. Therefore, when the first signs of aGvHD clinically manifest, the disease has been ongoing for several days at the cellular level, and the inflammatory cytokine cascade is fully activated. So, it comes as no surprise that to identify biomarker signatures for approaching this very complex task is a critical issue. In the past, we have already approached it through joint molecular and computational analyses of gene expression data proposing a computational framework for this disease. Notwithstanding this, there aren’t in literature quantitative measurements able to identify patterns or rules from these biomarkers or from aGvHD data, thus this is the first work about the issue. In this paper first we have applied different feature selection techniques, combined with different classifiers to detect the aGvHD at onset of clinical signs, then we have focused on the aGvHD scenario and in the knowledge discovery issue of the classification techniques used in the computational framework.

Ontology Based Personalized Modeling for Type 2 Diabetes Risk Analysis: An Integrated Approach

A novel ontology based type 2 diabetes risk analysis system framework is described, which allows the creation of global knowledge representation (ontology) and personalized modeling for a decision support system. A computerized model focusing on organizing knowledge related to three chronic diseases and genes has been developed in an ontological representation that is able to identify interrelationships for the ontology-based personalized risk evaluation for chronic diseases. The personalized modeling is a process of model creation for a single person, based on their personal data and the information available in the ontology. A transductive neuro-fuzzy inference system with weighted data normalization is used to evaluate personalized risk for chronic disease. This approach aims to provide support for further discovery through the integration of the ontological representation to build an expert system in order to pinpoint genes of interest and relevant diet components.

Integrating neural networks and chaotic measurements for modelling epileptic brain

In the last 20 years a lot of works in literature analysed and proposed several methods capable to predict the occurrence of seizures from the electroencephalogram (EEG) of epileptic patients. One of the best results was obtained using a version of the maximum Lyapunov exponent (Lmax) for predicting the advent of a seizure, but in spite of promising results presented, more recent evaluations could not reproduce these optimistic findings. Following this trend, in this paper we propose a new integrative technique starting from two different paradigms: Chaos and Neural Networks (NN). The new framework has been tested on long term intracerebral stereo-EEG (sEEG) recordings, with very good results. We present this way of analysis as the key for modelling brain mechanisms during epileptic seizures, going over critical state reported in literature for Lmax with suited computational methods, providing theoretical justifications. This is a preliminary work with numerous possible evolutions.

A molecular and computational diagnostic approach identifies FOXP3, ICOS, CD52 and CASP1 as the most informative biomarkers in acute graft-versus-host disease

Background Acute graft-versus-host disease is a severe complication of allogeneic stem cell transplantation in which the functional immune cells of the donor recognize the recipient as foreign and mount an immunological attack. There is an urgent need for better diagnostic instruments for the assessment of acute graft-versus-host disease. In the present study, a novel bioinformatics framework was used to identify gene expression patterns associated with acute graft-versushost disease in patients undergoing allogeneic hematopoietic stem cell transplantation. Design and Methods Peripheral blood cells were collected prospectively from patients who did develop acute graftversus-host disease (YES) and from those who did not (NO). Gene expression profiling was performed using a panel of 47 candidate genes potentially involved in alloreactive responses. The entire population of YES/NO acute graft-versus-host disease patients formed the experimental validation set. Personalized modeling based on a gene selection technique was applied to identify the most significant mRNA transcripts, which were then used to profile individual data samples for training and testing the classification/prediction framework. Results A leave-one-out cross-validation procedure was performed to investigate the robustness of the classification framework producing the following results: 100% on the training dataset and 97% on the testing dataset. According to our integrated methodology, transcripts for FOXP3, ICOS, CD52 and CASP1, genes involved in immune alloreactive responses and participating in immune cell interactions, were identified as the most informative biomarkers in allogeneic stem cell transplant recipients experiencing acute graft-versus-host disease. Conclusions This study demonstrates that the integrated methodology proposed is useful for the selection of valid gene targets for the diagnosis of acute graft-versus-host disease, producing satisfactory accuracy over independent clinical features of the allogeneic transplanted population.

Advances in medical decision support systems for diagnosis of acute graft-versus-host disease: molecular and computational intelligence joint approaches

Acute graft-versus-host disease (aGVHD) is a serious systemic complication of allogeneic hematopoietic stem cell transplantation (HSCT) causing considerable morbidity and mortality. Acute GVHD occurs when alloreactive donor-derived T cells recognize host-recipient antigens as foreign. These trigger a complex multiphase process that ultimately results in apoptotic injury in target organs. The early events leading to GVHD seem to occur very soon, presumably within hours from the graft infusion. Therefore, when the first signs of aGVHD clinically manifest, the disease has been ongoing for several days at the cellular level, and the inflammatory cytokine cascade is fully activated. So, it comes as no surprise that progress in treatment based on clinical diagnosis of aGVHD has been limited in the past 30 years. It is likely that a pre-emptive strategy using systemic high-dose corticosteroids as early as possible could improve the outcome of aGVHD. Due to the deleterious effects of such treatment particularly in terms of infection risk posed by systemic steroid administration in a population that is already immune-suppressed, it is critical to identify biomarker signatures for approaching this very complex task. Some research groups have begun addressing this issue through molecular and proteomic analyses, combining these approaches with computational intelligence techniques, with the specific aim of facilitating the identification of diagnostic biomarkers in aGVHD. In this review, we focus on the aGVHD scenario and on the more recent state-of-the-art. We also attempt to give an overview of the classical and novel techniques proposed as medical decision support system for the diagnosis of GVHD.

Machine learning and personalized modeling based gene selection for acute GvHD gene expression data analysis

In this paper a novel gene selection method based on personalized modeling is proposed and is compared with classical machine learning techniques to identify diagnostic gene targets and to use them for a successful diagnosis of a medical problem - acute graft-versus-host disease (aGvHD). An analysis using the integrated approach of new data with the existing models is evaluated. Identifying a compact set of genes from gene expression data is a critical step in bioinformatics research. Personalized modeling is a recently introduced technique for constructing clinical decision support systems. This is a novel study which utilises both computational and biological evidence and the use of a personalized modeling for the analysis of this disease. Directions for further studies are also outlined.

A comparison between neural networks and k-nearest neighbours for blood cells taxonomy

Constitutive properties of living cells are able to withstand physiological environment as well as mechanical stimuli occurring within and outside the body. Any deviation from these properties would undermine the physical integrity of the cells as well as their biological functions. Thus, a quantitative study in single cell mechanics needs to be conducted. In this paper we will examine fluid flow and Neo–Hookean deformation related to the rolling effect. A mechanical model to describe the cellular adhesion with detachment is here proposed. We develop a first finite element method (FEM) analysis, simulating blood cells attached on vessel wall. Restricting the interest on the contact surface and elaborating again the computational results, we develop an equivalent spring model. Our opinion is that the simulation notices deformation inhomogeneities, i.e., areas with different concentrations having different deformation values. This important observation should be connected with a specific form of the stored energy deformation. In this case, it loses the standard convexity to show a non-monotone deformation law. Consequently, we have more minima and the variational problem seems more difficult. Several numerical simulations have been carried out, involving a number of human cells with different mechanical properties. All the collected data have been subsequently used to train and test suitable soft computing models in order to classify the kind of cell. Obtained results assure good performances (4.7% of classification error) of the implemented classifier, with very interesting applications.

Hematopoietic stem cells for neovascularization and wound repair

Background It is now well-known that a critical part of normal healing for cutaneous wounds is the formation of new blood vessels. As implantation of autologous bone marrow (BM)-derived Endothelial Progenitor Cells (EPC) into ischemic limbs has become a promising treatment for moderate to severe peripheral arterial occlusive disease (PAD), we have begun a Phase II randomized trial in Type 2 diabetes mellitus (T2DM). The goal of infusions is to promote neoangiogenesis, thereby increasing circulation, reducing symptoms, and facilitating wound healing. At first, we have studied EPC and gene expression profile (GEP) of peripheral blood, hypothesizing that it is possible to identify useful markers for the assessment of the severity of endothelial dysfunction.