Student opportunities

THESIS MSc
Bio-Inspired methods allow to optimize also complex systems when the optimum cannot be found with exact approaches. They are inspired by some natural process, such as Charles Darwin’s evolution theory. On the other side Rule-Based Control aims at optimizing complex systems by using a rule-based model obtained directly by the data. In this way, an explicit form of the cost function is not needed, increasing the range of potential applications. In this project the student will:

• Study the state-of-the-art of Bio-Inspired methods
• Definition of a case study in the field of public transport scheduling
• Developing analysis workflows for optimizing the network
• Analysing the results and optimizing the performances

THESIS BSc/MSc
Rule-based decision methods are becoming crucial in modern process automation system since they allow expert users to understand the mechanism used by the machine to take decisions. Moreover, integration to manual rules (discovered by humans) and automatic rules (discovered by the machine) is a key point for improving automatic decision processes. To this aim, it is essential to transform the space of the rules into a metric space, in order to allow operations such as distance computation.
The student will:

• Study a way to evaluate the distance between sets of rules
• Implement these definitions
• Design a case study to evaluate the effectiveness of this approach
• Perform the tests and evaluate the results

THESIS MSc
Efficient management of pedestrian traffic in urban areas is crucial for creating safe, accessible, and well-organized public spaces. Traditional methods of pedestrian analysis often fall short in capturing the complexities of crowd dynamics and pedestrian behavior. GCNs, which have demonstrated success in various fields, hold promise for modeling and understanding the intricate relationships in pedestrian networks.
During the activity the student will:

• Get advanced insights into the application of GCNs for modeling pedestrian traffic in urban environments.
• Design and implement tailored GCN models for pedestrian traffic analysis and urban planning.
• Design and implement case studies showcasing the practical benefits of GCN-based pedestrian traffic analysis.
• Get knowledge on the deployment of synthetic datasets for research and experimentation.

THESIS BSc/MSc
Explainability of machine learning algorithms is one of the most important challenges in today Artificial Intelligence. As a matter of fact, understandable models can be audited by expert human users, allowing a quicker and sounder implementation in automated decision systems. Rulex has developed an innovative rule-based machine learning algorithm, named Logic Learning Machine. The objective of the thesis is to develop an algorithm independent sequential ensemble approach and to apply it to Logic Learning Machine to improve the prediction ability. These are the main activities:

• Using the Rulex platform, developing a workflow for the generation of ensembles of classifiers and sequentially applying them to a dataset
• Applying this workflow to Logic Learning Machine
• Test the approach to some benchmark dataset and compare with results obtained with standard methods

THESIS MSc
Among the pillar applications in supervised learning, we have classification, for which the target variable can assume a finite set of unordered values and regression, for which the target variable can assume an infinite set of ordered values. Yet, an in-between, practically very relevant case exists: ordinal regression. In this case, the target variable can assume a finite set of values, but these values are somehow ordered. For example, different degrees of risk. The candidate will explore state-of-the-art techniques in ordinal regression, having the chance also to study and experiment the adaptation of the Logic Learning Machine algorithm [1], currently available to address classification and regression problems, also to this case.

[1] Muselli M, & Ferrari E. (2011) Coupling logical analysis of data and shadow clustering for partially defined positive Boolean function reconstruction. IEEE Transaction on Knowledge and Data Engineering

THESIS MSc
Understanding the contents of written documents, including the contextual nuances, is a very challenging task and involves linguistics, computer science and artificial intelligence. Recently, the broad diffusion of efficient deep learning models has allowed to develop new algorithm for NLP which are based on the analysis of big text corpora to extract semantical and logical relationships within a text. In particular, recurrent neural networks have become quite popular since they allow to consider not only the single words but also their sequence within each sentence. During this internship/thesis a RNN model will be implemented and tested starting from publicly available corpora.

THESIS MSc
Detecting anomalies in a set of data is a crucial task almost all application field. Sometimes anomalies are manually flagged by human users that, thanks to their experience, are able to distinguish regular cases from anomalous ones. Nevertheless, in most cases anomalies are hidden in the data and should be discovered without any human supervision. For this reason, unsupervised methods for anomaly detection have been extensively studied in the last years. One possible choice is given by auto-encoding methods that compare the prediction provided by supervised methods with the actual one to determine the level of anomaly of a pattern. Different supervised methods can be used in this context. In this thesis the student will explore the possibility of using a rule-based classification method. In particular, the student will:

• Study a way to use autoencoding rule-based methods to detect anomalies
• Implement these definitions
• Design a case study to evaluate the effectiveness of this approach
• Perform the tests and evaluate the results

THESIS MSc
The problem of incorrect data is a big challenge for most companies since it affects all the data-based decision processes resulting in higher costs. Robotic Data Correction (RDC) is an innovative tool, developed by Rulex, to automatically correct data. RDC is a general-purpose tool that corrects also interdependent errors in data. The activities to be carried in the thesis are related to one or more of these objectives:

• Exploring new applications of RDC
• Extending the application of RDC to ordered variables
• Developing analysis workflow ready to be deployed in real world scenarios

The candidate will study how RDC works, develop some improvements to the current methods and test their effectiveness on real world and/or synthetic data.

THESIS MSc
Description: This thesis project aims to investigate the use of Generative Adversarial Networks (GANs) for image augmentation, a technique used to artificially increase the size and diversity of image datasets. GANs consist of two neural networks, the generator and the discriminator, which compete against each other to produce realistic images. By training a GAN on existing image datasets, we can generate new, synthetic images that closely resemble real data, thereby enhancing the robustness and diversity of the dataset.

The student will carry out this activities:

• Literature Review: Explore existing research on GANs and image augmentation techniques to understand the state-of-the-art methodologies and challenges.
• Data Preprocessing and Model Development: Collect and preprocess image datasets, and develop a GAN architecture suitable for image augmentation.
• Training and Evaluation: Train the GAN model on the dataset, fine-tune parameters, and evaluate the generated images' quality and diversity.
• Application and Analysis: Apply the augmented dataset to a real-world image classification or object detection task, and analyze the performance improvements achieved through GAN-based augmentation.

THESIS BSc/MSc
Description: This thesis project focuses on harnessing deep learning techniques for the analysis of satellite images, aiming to extract meaningful insights and information from vast collections of Earth observation data. Deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have shown remarkable capabilities in image recognition, object detection, and semantic segmentation tasks. By applying these techniques to satellite imagery, we can unlock valuable knowledge about land use, environmental changes, urban development, and natural disasters.

The student will carry out this activities:

• Dataset Acquisition and Preprocessing: Obtain satellite image datasets from reputable sources and preprocess the data to ensure consistency, quality, and compatibility with deep learning models.
• Model Selection and Architecture Design: Investigate various deep learning architectures suitable for satellite image analysis, considering factors such as model complexity, computational efficiency, and task-specific requirements.
• Training and Validation: Train the selected deep learning models on the prepared dataset, fine-tune hyperparameters, and validate the models' performance using appropriate evaluation metrics.
• Application and Interpretation: Apply the trained models to real-world satellite image analysis tasks, such as land cover classification, vegetation monitoring, urban growth detection, and disaster response. Interpret the results and assess the practical utility of deep learning techniques in addressing relevant challenges.

THESIS MSc
Chess, known for its rich history and strategic complexity, has long been a subject of fascination for enthusiasts and scholars alike. To gain insights into the performance of chess players across time, historical data can serve as a valuable resource. The aim of this project is to analyze historical chess player performance data and uncover trends, patterns, and key milestones in the world of chess.

The outcome of this research project will be a comprehensive analysis of chess player performance throughout history. This analysis will include:

• Identification of influential chess players who made significant contributions to the game.
• Evaluation of player performance metrics, such as Elo ratings, tournament victories, and match outcomes.
• Examination of the evolution of chess strategies and opening moves.
• Insights into how technological advancements, such as computer analysis, have impacted chess.

THESIS BSc
A distributed system in cloud applications is a set of different containers which runs different codes in a correlated way, with a high level of internal communication between the parts. We used Microservices are referred to as containers exploiting a particular operation inside our system. The main used system of communication in microservices distributed system is the AMQP protocol, a broker mediated protocol that allows a high level of control about message retaining, queueing and exchange. The main AMQP broker used in many commercial and open-source application is RabbitMQ. Scope of the thesis is to study this type of communication in a complex microservice structure where many types of different queues and exchange are present and where a high level of security and performance is strictly required. After a benchmark testing phase the broker configuration will be optimized to speed up the whole system, using the most advanced data analysis technique available on the market.

THESIS BSc
In many Data Analysis applications not homogeneous data need to be treated. Data spans from number to images, from text to geographical coordinates and for each of these types of particular operations need to be implemented and offered to Data Scientists. One of the most difficult challenges in Data Analysis is data graphical representation: data are mostly visualised through a table grid, sometimes ill represented in a grid cell. The scope of this thesis is to implement a general approach to store any form of derived data (images, geographical coordinates, credit card number and so on) in a column table maintaining a fast and clear visualization. Users should be able to perform specific operations owned by the derived type (length between two geographical quantity, opacity filter for images and so on).

THESIS MSc
The most important feature of a distributed cloud application is the balance between its internal components. CPU and RAM are provided in a distributed form and the ability of the software itself to control the load between the various parts is the key feature of this type of architecture. To reach this goal, an estimate (given the operation) of the necessary CPU and RAM to complete it represents a primary input. However, in many complex scenarios a reliable estimate of such quantity is far from being trivial. The scope of this thesis project is to try to apply Machine Learning technique to this field to construct a Load Balancer Application. The Load Balancer Application will be able to learn for the precedent cases and apply autoregression techniques to better estimate the effort of any operation on the architecture itself.

THESIS MSc
Databases are the most used type of storage in data analysis, in cloud application and in software in general. They represent the most used storage class in almost all the possible fields. Databases are divided in SQL and NOSQL macro types. SQL Databases are more optimized in treating structure data but they depend on SQL syntax and they are far from being general: each SQL database distribution has its SQL syntax, its behaviour and its performance. Moreover, conflicts management (read/read, read/write, and write/write parallel access) is not treated correctly in many used distributions, leading to unexpected results in case of high parallelism as in any cloud application. For this reason, in recent years NOSQL database has grown up to fill this lack of old SQL database. NOSQL database relies on different file system logic. They allow not structured data to be stored more efficiently; they correctly treat conflict management and allow to perform simple query with high performance due to index replication. On the contrary however, they are extremely slow in fetching high quantity of data with respect to a standard SQL database, preventing them to be used in big data analysis cases. The scope of this thesis project is to implement a NOSQL database with some innovative ideas to speed up the fetching of data reducing as much as possible computation time and memory consumption (at least for simple single value queries). A comparison with standard SQL and NOSQL distribution will also be performed.

THESIS MSc
In machine learning, single and multivariate linear regression represent two of the most used algorithms to approximate a set of data with a fitting function. The searched function is a linear function in the single case, or a polynomial function in the latter. However, both the solutions return a continuous function which in some cases could be inaccurate, especially to treat fast changing process. The scope of this thesis project is to implement an innovative approach in which regression is applied searching for a piecewise linear function, with a fixed number of breakpoints. Later the behaviour of the piecewise approximation will be compared with single and multivariate solution and with other ML regression system as LLM, SVM and Neural Network.

THESIS MSc
Anti-Money Laudering is one of the most relevant topics among financial applications which could benefit from the adoption of advanced data analytics and modeling techniques. In 2023, the SythAML and the IBM Transactions for Anti Money Laundering (AML) datasets have been released (see "A synthetic data set to benchmark anti-money laundering methods" and www.kaggle.com/datasets/...) and provides a robust benchmark to analyze and compare different predictive techniques.

In the proposed internship/thesis, the candidate will:

• Explore the state of the art in Anti-Money Laundering techniques
• Apply standard models (such as logistic regression) to the benchmark dataset, both by means of programming languages (Python, for instance), or by means of the self-coding Rulex Platform software
• Explore innovative approaches on the same dataset, comparing the outcomes. These experimentations will be essentially liked to the adoption of interpretable models (such as Logic Learning Machine) and to the enrichment of the dataset through graph processing techniques

THESIS MSc
Many decisions, both individual (trading) and organizational (resource allocation) are driven by a careful analysis of balance sheet data. Together with classical techniques, which involve the computation of some well-known indices, also machine learning approaches, which allow a richer insight on the situation, are growing in popularity. The candidate will investigate available ML balance sheet analysis techniques and will have the chance to develop an analysis pipeline of this kind without the need to write code, using the visual programming techniques of Rulex Platform.

THESIS MSc
Financial markets are not only driven by quantitative data but also heavily influenced by qualitative information. NLP, a branch of artificial intelligence, specializes in understanding and processing human language, making it a valuable tool for extracting knowledge from textual financial sources. The integration of NLP techniques can offer a competitive edge by identifying market-moving events, sentiment shifts, and hidden patterns within textual financial data.

The thesis activities will include:

• Collection of a proper set of data including e.g. financial news, earning reports, social media content...
• Implementation of NLP models for the analysis of the textual data.
• Analysis of sentiment scores to measure market sentiment about news and events.
• Perform predictive analysis using NLP-derived features.
• Interpret research findings and evaluate the potential impact of NLP technologies.