Davide De March

Designing Lead Optimisation of MMP-12 Inhibitors

The design of new molecules with desired properties is in general a very difficult problem, involving heavy experimentation with high investment of resources and possible negative impact on the environment. The standard approach consists of iteration among formulation, synthesis, and testing cycles, which is a very long and laborious process. In this paper we address the so-called lead optimisation process by developing a new strategy to design experiments and modelling data, namely, the evolutionary model-based design for optimisation (EDO). This approach is developed on a very small set of experimental points, which change in relation to the response of the experimentation according to the principle of evolution and insights gained through statistical models. This new procedure is validated on a data set provided as test environment by Pickett et al. (2011), and the results are analysed and compared to the genetic algorithm optimisation (GAO) as a benchmark. The very good performance of the EDO approach is shown in its capacity to uncover the optimum value using a very limited set of experimental points, avoiding unnecessary experimentation.

Response improvement in complex experiments by co-information composite likelihood optimization

We propose an adaptive procedure for improving the response outcomes of complex combinatorial experiments. New experiment batches are chosen by minimizing the co-information composite likelihood (COIL) objective function, which is derived by coupling importance sampling and composite likelihood principles. We show convergence of the best experiment within each batch to the globally optimal experiment in finite time, and carry out simulations to assess the convergence behavior as the design space size increases. The procedure is tested as a new enzyme engineering protocol in an experiment with a design space size of order 107.

A Predictive Approach Based on Neural Network Models for Building Automation Systems

In this paper we address the problem of developing a control strategy to reduce the building energy consumption and reach indoor comfort levels. For this multiple and conflicting objectives optimisation we develop an approach based on stochastic feed-forward neural network models with ARIMA model predictions considered as input variables for networks. Studying real data from a sensorised office located in Rovereto (Italy) we develop the approach and achieve results exhibiting the very good performance of this predictive procedure.

Qualitative Particle Swarm Optimization (Q-PSO) for Energy-Efficient Building Designs

Particle Swarm Optimization (PSO) is a stochastic optimization method, based on the social behavior of bird flocks. The method, known for its high performance in optimization, has been mainly developed for problems involving just quantitative variables. In this paper we propose a new approach called Qualitative Particle Swarm Optimization (Q-PSO) where the variables in the optimization can be both qualitative and quantitative and the updating rule is derived adopting probabilistic measures. We apply this procedure to a complex engineering optimization problem concerning building facade design. More specifically, we address the problem of deriving an energy-efficient building design, i.e. a design that minimizes the energy consumption (and the emission of carbon dioxide) for heating, cooling and lighting. We develop a simulation study to evaluate Q-PSO procedure and we derive comparisons with most conventional approaches. The study shows a very good performance of our approach in achieving the assigned target.

Determining the Relationship Between Co-creation and Innovation by Neural Networks

The growing complexity of markets, business development and administration has fostered the application of more sophisticated quantitative methods aiming at the analysis of common features and differences amongst different businesses. Amongst those quantitative methods, Neural Networks are gaining support of both practitioners and scholars. This is due to their generalisation capabilities which make them apt to be used without any preliminary assumptions about the variables at hand or about the specific types of the corresponding models. To this extent, we are using them to classify firms w.r.t. the relationship between the perception of their innovativeness and the degree of their involvement in value co-creation activities—the extent to which they involve end users in the definition of their final products and services. We will show that businesses from specific sectors could have a higher degree of involvement in value co-creation. The mapping between the type of firms and the degree of their involvement in value co-creation is of particular interest since they describe attributes and activities and a completely different heuristic level. We have also studied businesses belonging to stock Exchange indexes, which are regarded as the specimen of the economic and financial situation of a Country. Our main contribution will be in translating the applicability of ANN in innovation research.

Agent-Based Model to Simulate Groundwater Remediation with Nanoscale Zero Valent Iron

Soils, air and water have been deeply contaminated by anthropogenic activities continuously spread over time. One of the most dangerous pollutant in groundwater is represented by chlorinated organic solvents, which acts as a Dense Non Aquifer Phase Liquid (DNAPL) contaminant. Many laboratory experiments have shown that nZVI encapsulated into micelles could treat DNAPL pollution directly into the groundwater but very few in situ experimentations have been tested. Agent-Based Model (ABM) is a powerful tool to simulate and to gain better insights in complex systems. In this paper we present an ABM simulation of DNAPL contaminated groundwater remediation. The model simulates a dehalogenation process of Trichloroethylene (TCE) with the application of encapsulated nZVI, directly injected into the DNAPL contaminant source.