Lorenzo Menculini

In this work, we describe in detail how Deep Learning and Computer Vision can help to detect fault events of the AirTender system, an aftermarket motorcycle damping system component. One of the most effective ways to monitor the AirTender functioning is to look for oil stains on its surface. Starting from real-time images, AirTender is first detected in the motorbike suspension system, simulated indoor, and then, a binary classifier determines whether AirTender is spilling oil or not. The detection is made with the help of the Yolo5 architecture, whereas the classification is carried out with the help of a suitably designed Convolutional Neural Network, OilNet40. In order to detect oil leaks more clearly, we dilute the oil in AirTender with a fluorescent dye with an excitation wavelength peak of approximately 390 nm. AirTender is then illuminated with suitable UV LEDs. The whole system is an attempt to design a low-cost detection setup. An on-board device, such as a mini-computer, is placed near the suspension system and connected to a full hd camera framing AirTender. The on-board device, through our Neural Network algorithm, is then able to localize and classify AirTender as normally functioning (non-leak image) or anomaly (leak image).

In this work, we describe in detail how Deep Learning and Computer Vision can help to detect fault events of the AirTender system, an aftermarket motorcycle damping system component. One of the most effective ways to monitor the AirTender functioning is to look for oil stains on its surface. Starting from real-time images, AirTender is first detected in the motorbike suspension system, simulated indoor, and then, a binary classifier determines whether AirTender is spilling oil or not. The detection is made with the help of the Yolo5 architecture, whereas the classification is carried out with the help of a suitably designed Convolutional Neural Network, OilNet40. In order to detect oil leaks more clearly, we dilute the oil in AirTender with a fluorescent dye with an excitation wavelength peak of approximately 390 nm. AirTender is then illuminated with suitable UV LEDs. The whole system is an attempt to design a low-cost detection setup. An on-board device, such as a mini-computer, is placed near the suspension system and connected to a full hd camera framing AirTender. The on-board device, through our Neural Network algorithm, is then able to localize and classify AirTender as normally functioning (non-leak image) or anomaly (leak image).

Setting sale prices correctly is of great importance for firms, and the study and forecast of prices time series is therefore a relevant topic not only from a data science perspective but also from an economic and applicative one. In this paper, we examine different techniques to forecast sale prices applied by an Italian food wholesaler, as a step towards the automation of pricing tasks usually taken care by human workforce. We consider ARIMA models and compare them to Prophet, a scalable forecasting tool by Facebook based on a generalized additive model, and to deep learning models exploiting Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs). ARIMA models are frequently used in econometric analyses, providing a good benchmark for the problem under study. Our results indicate that ARIMA models and LSTM neural networks perform similarly for the forecasting task under consideration, while the combination of CNNs and LSTMs attains the best overall accuracy, but requires more time to be tuned. On the contrary, Prophet is quick and easy to use, but considerably less accurate.

Quantum annealing has emerged in the last few years as a promising quantum computing approach to solving large-scale combinatorial optimization problems. In this paper, we formulate the problem of correctly placing pressure sensors on a Water Distribution Network (WDN) as a combinatorial optimization problem in the form of a Quadratic Unconstrained Binary Optimization (QUBO) or Ising model. Optimal sensor placement is indeed key to detect and isolate fault events. We outline the QUBO and Ising formulations for the sensor placement problem starting from the network topology and few other features. We present a detailed procedure to solve the problem by minimizing its Hamiltonian using PyQUBO, an open-source Python Library. We then apply our methods to the case of a real Water Distribution Network. Both simulated annealing and a hybrid quantum-classical approach on a D-Wave machine are employed.

Non-relativistic string theories promise to provide simpler theories of quantum gravity as well as tractable limits of the AdS/CFT correspondence. However, several apparently distinct non-relativistic string theories have been constructed. In particular, one approach is to reduce a relativistic string along a null isometry in target space. Another method is to perform an appropriate large speed of light expansion of a relativistic string. Both of the resulting non-relativistic string theories only have a well-defined spectrum if they have nonzero winding along a longitudinal spatial direction. In the presence of a Kalb-Ramond field, we show that these theories are equivalent provided the latter direction is an isometry. Finally, we consider a further limit of non-relativistic string theory that has proven useful in the context of AdS/CFT (related to Spin Matrix Theory). In that case, the worldsheet theory itself becomes non-relativistic and the dilaton coupling vanishes.

Non-relativistic string theories promise to provide simpler theories of quantum gravity as well as tractable limits of the AdS/CFT correspondence. However, several apparently distinct non-relativistic string theories have been constructed. In particular, one approach is to reduce a relativistic string along a null isometry in target space. Another method is to perform an appropriate large speed of light expansion of a relativistic string. Both of the resulting non-relativistic string theories only have a well-defined spectrum if they have nonzero winding along a longitudinal spatial direction. In the presence of a Kalb--Ramond field, we show that these theories are equivalent provided the latter direction is an isometry. Finally, we consider a further limit of non-relativistic string theory that has proven useful in the context of AdS/CFT (related to Spin Matrix Theory). In that case, the worldsheet theory itself becomes non-relativistic and the dilaton coupling vanishes.

We find a Polyakov-type action for strings moving in a torsional Newton-Cartan geometry. This is obtained by starting with the relativistic Polyakov action and fixing the momentum of the string along a non-compact null isometry. For a flat target space, we show that the world-sheet theory becomes the Gomis-Ooguri action. From a target space perspective these strings are non-relativistic but their world-sheet theories are still relativistic. We show that one can take a scaling limit in which also the world-sheet theory becomes non-relativistic with an infinite-dimensional symmetry algebra given by the Galilean conformal algebra. This scaling limit can be taken in the context of the AdS/CFT correspondence and we show that it is realized by the ‘Spin Matrix Theory’ limits of strings on AdS₅ × S ⁵. Spin Matrix theory arises as non-relativistic limits of the AdS/CFT correspondence close to BPS bounds. The duality between non-relativistic strings and Spin Matrix theory provides a holographic duality of its own and points towards a framework for more tractable holographic dualities whereby non-relativistic strings are dual to near BPS limits of the dual field theory.