Machine Learning algorithm on seat comfort level measurement, mapping pressure values with body regions

The comfort level of the seat has a major effect on the usage of a vehicle; thus, car manufacturers have been working on elevating car seat comfort as much as possible. However, still, the testing and evaluation of comfort are done using exhaustive trial and error testing and evaluation of data. In this thesis, we resort to machine learning and Artificial Neural Networks (ANN) to develop a fully automated approach. Even though this approach has its advantages in minimizing time and using a large set of data, it takes away the degree of freedom of the engineer on making decisions. The focus of this study is on filling the gap in a two-step comfort level evaluation which used pressure mapping with body regions to evaluate the average pressure supported by specific body parts and the Self-Assessment Exam (SAE) questions on evaluation of the person’s interest. This study has created a machine learning algorithm that works on giving a degree of freedom to the engineer in making a decision when mapping pressure values with body regions using ANN. The mapping is done with 92% accuracy and with the help of a Graphical User Interface (GUI) that facilitates the process during the testing time of comfort level evaluation of the car seat, which decreases the duration of the test analysis from days to hours.

Extracting FSA descriptions of robot behaviours from the dynamics of automatically designed controller networks

Automatic design has become a common approach to evolve complex networks, such as artificial neural networks (ANNs) and random boolean networks (RBNs), and many evolutionary setups have been discussed to increase the efficiency of this process. However networks evolved in this way have few limitations that should not be overlooked. One of these limitations is the black-box problem that refers to the impossibility to analyze internal behaviour of complex networks in an efficient and meaningful way. The aim of this study is to develop a methodology that make it possible to extract finite-state automata (FSAs) descriptions of robot behaviours from the dynamics of automatically designed complex controller networks. These FSAs unlike complex networks from which they're extracted are both readable and editable thus making the resulting designs much more valuable.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Tree regularized neural networks for key point analysis

This thesis contributes to the ArgMining 2021 shared task on Key Point Analysis. Key Point Analysis entails extracting and calculating the prevalence of a concise list of the most prominent talking points, from an input corpus. These talking points are usually referred to as key points. Key point analysis is divided into two subtasks: Key Point Matching, which involves assigning a matching score to each key point/argument pair, and Key Point Generation, which consists of the generation of key points. The task of Key Point Matching was approached using different models: a pretrained Sentence Transformers model and a tree-constrained Graph Neural Network were tested. The best model was the fine-tuned Sentence Transformers, which achieved a mean Average Precision score of 0.75, ranking 12 compared to other participating teams. The model was then used for the subtask of Key Point Generation using the extractive method in the selection of key point candidates and the model developed for the previous subtask to evaluate them.

Generative Neural Networks for image iper-resolution and improvement of Optical Character Recognition's performances

The usage of Optical Character Recognition’s (OCR, systems is a widely spread technology into the world of Computer Vision and Machine Learning. It is a topic that interest many field, for example the automotive, where becomes a specialized task known as License Plate Recognition, useful for many application from the automation of toll road to intelligent payments. However, OCR systems need to be very accurate and generalizable in order to be able to extract the text of license plates under high variable conditions, from the type of camera used for acquisition to light changes. Such variables compromise the quality of digitalized real scenes causing the presence of noise and degradation of various type, which can be minimized with the application of modern approaches for image iper resolution and noise reduction. Oneclass of them is known as Generative Neural Networks, which are very strong ally for the solution of this popular problem.

Statistical Mechanics of Monomer-Dimer Models on Complete and Erdös-Rényi Graphs

Nella tesi sono trattate due famiglie di modelli meccanico statistici su vari grafi: i modelli di spin ferromagnetici (o di Ising) e i modelli di monomero-dimero. Il primo capitolo è dedicato principalmente allo studio del lavoro di Dembo e Montanari, in cui viene risolto il modello di Ising su grafi aleatori. Nel secondo capitolo vengono studiati i modelli di monomero-dimero, a partire dal lavoro di Heilemann e Lieb,con l'intento di dare contributi nuovi alla teoria. I principali temi trattati sono disuguaglianze di correlazione, soluzioni esatte su alcuni grafi ad albero e sul grafo completo, la concentrazione dell'energia libera intorno al proprio valor medio sul grafo aleatorio diluito di Erdös-Rényi.

Statistical mechanics of polymer models: rigorous results and applications

Monomer-dimer models are amongst the models in statistical mechanics which found application in many areas of science, ranging from biology to social sciences. This model describes a many-body system in which monoatomic and diatomic particles subject to hard-core interactions get deposited on a graph. In our work we provide an extension of this model to higher-order particles. The aim of our work is threefold: first we study the thermodynamic properties of the newly introduced model. We solve analytically some regular cases and find that, differently from the original, our extension admits phase transitions. Then we tackle the inverse problem, both from an analytical and numerical perspective. Finally we propose an application to aggregation phenomena in virtual messaging services.

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose to learn a variable selection policy for branch-and-bound in mixed-integer linear programming, by imitation learning on a diversified variant of the strong branching expert rule. We encode states as bipartite graphs and parameterize the policy as a graph convolutional neural network. Experiments on a series of synthetic problems demonstrate that our approach produces policies that can improve upon expert-designed branching rules on large problems, and generalize to instances significantly larger than seen during training.

Models for the assessment of resilience in water distribution networks

The following thesis work focuses on the use and implementation of advanced models for measuring the resilience of water distribution networks. In particular, the functions implemented in GRA Tool, a software developed by the University of Exeter (UK), and the functions of the Toolkit of Epanet 2.2 were investigated. The study of the resilience and failure, obtained through GRA Tool and the development of the methodology based on the combined use of EPANET 2.2 and MATLAB software, was tested in a first phase, on a small-sized literature water distribution network, so that the variability of the results could be perceived more clearly and with greater immediacy, and then, on a more complex network, that of Modena. In the specific, it has been decided to go to recreate a mode of failure deferred in time, one proposed by the software GRA Tool, that is failure to the pipes, to make a comparison between the two methodologies. The analysis of hydraulic efficiency was conducted using a synthetic and global network performance index, i.e., Resilience index, introduced by Todini in the years 2000-2016. In fact, this index, being one of the parameters with which to evaluate the overall state of "hydraulic well-being" of a network, has the advantage of being able to act as a criterion for selecting any improvements to be made on the network itself. Furthermore, during these analyzes, was shown the analytical development undergone over time by the formula of the Resilience Index. The final intent of this thesis work was to understand by what means to improve the resilience of the system in question, as the introduction of the scenario linked to the rupture of the pipelines was designed to be able to identify the most problematic branches, i.e., those that in the event of a failure it would entail greater damage to the network, including lowering the Resilience Index.