Sviluppo di un sistema per allocazione e scheduling di applicazioni periodiche

In questa tesi, viene illustrato un metodo risolutivo al problema dell’allocazione e schedulazione, su risorse eterogenee con capacità unaria rinnovabile e cumulativa non rinnovabile, di applicazioni multitask periodiche, con periodi in relazione armonica, strutturate in attività indipendenti o sottoposte a vincoli di precedenza e con durate dipendenti dalla specifica risorsa di allocazione. L’obiettivo è quello di fornire un’implementazione del modello in grado di gestire l’allocazione e la schedulazione di istanze (i.e. insieme di applicazioni) variabili, caratterizzate da una serie di parametri. La struttura implementativa, realizzata secondo la Logic-based Benders decomposition, prevede la suddivisione del problema in due moduli. Il primo in grado di generare un’allocazione e realizzato con tecniche di programmazione lineare intera mista, il secondo con lo scopo di controllare l’ammissibilità di tale allocazione attraverso una schedulazione ottima e realizzato mediante tecniche di programmazione a vincoli. Il meccanismo di comunicazione tra i due moduli avviene mediante vincoli lineari, denominati tagli di Benders, che vengono aggiunti dopo ogni iterazione del sistema. L’efficacia del modello sarà valutata confrontando i risultati ottenuti attraverso una serie di test, con i valori forniti da un metodo di allocazione e schedulazione alternativo.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

Anomaly Detection in Noisy Images

Finding rare events in multidimensional data is an important detection problem that has applications in many fields, such as risk estimation in insurance industry, finance, flood prediction, medical diagnosis, quality assurance, security, or safety in transportation. The occurrence of such anomalies is so infrequent that there is usually not enough training data to learn an accurate statistical model of the anomaly class. In some cases, such events may have never been observed, so the only information that is available is a set of normal samples and an assumed pairwise similarity function. Such metric may only be known up to a certain number of unspecified parameters, which would either need to be learned from training data, or fixed by a domain expert. Sometimes, the anomalous condition may be formulated algebraically, such as a measure exceeding a predefined threshold, but nuisance variables may complicate the estimation of such a measure. Change detection methods used in time series analysis are not easily extendable to the multidimensional case, where discontinuities are not localized to a single point. On the other hand, in higher dimensions, data exhibits more complex interdependencies, and there is redundancy that could be exploited to adaptively model the normal data. In the first part of this dissertation, we review the theoretical framework for anomaly detection in images and previous anomaly detection work done in the context of crack detection and detection of anomalous components in railway tracks. In the second part, we propose new anomaly detection algorithms. The fact that curvilinear discontinuities in images are sparse with respect to the frame of shearlets, allows us to pose this anomaly detection problem as basis pursuit optimization. Therefore, we pose the problem of detecting curvilinear anomalies in noisy textured images as a blind source separation problem under sparsity constraints, and propose an iterative shrinkage algorithm to solve it. Taking advantage of the parallel nature of this algorithm, we describe how this method can be accelerated using graphical processing units (GPU). Then, we propose a new method for finding defective components on railway tracks using cameras mounted on a train. We describe how to extract features and use a combination of classifiers to solve this problem. Then, we scale anomaly detection to bigger datasets with complex interdependencies. We show that the anomaly detection problem naturally fits in the multitask learning framework. The first task consists of learning a compact representation of the good samples, while the second task consists of learning the anomaly detector. Using deep convolutional neural networks, we show that it is possible to train a deep model with a limited number of anomalous examples. In sequential detection problems, the presence of time-variant nuisance parameters affect the detection performance. In the last part of this dissertation, we present a method for adaptively estimating the threshold of sequential detectors using Extreme Value Theory on a Bayesian framework. Finally, conclusions on the results obtained are provided, followed by a discussion of possible future work.

Multi-task transfer learning for in hospital-death prediction for ICU patients

Multi-Task Transfer Learning (MTTL) is an efficient approach for learning from inter-related tasks with small sample size and imbalanced class distribution. Since the intensive care unit (ICU) data set (publicly available in Physionet) has subjects from four different ICU types, we hypothesizethat there is an underlying relatedness amongst various ICU types. Therefore, this study aims to explore MTTL model for in-hospital mortality prediction of ICU patients. We used singletask learning (STL) approach on the augmented data as well as individual ICU data and compared the performance with the proposed MTTL model. As a performance measurement metrics, we used sensitivity (Sens), positive predictivity (+Pred), and Score. MTTL with class balancing showed the best performance with score of 0.78, 0.73, o.52 and 0.63 for ICU type 1(Coronary care unit), 2 (Cardiac surgery unit), 3 (Medical ICU) and 4 (Surgical ICU) respectively. In contrast the maximum score obtained using STL approach was 0.40 for ICU type 1 & 2. These results indicates that the performance of in-hospital mortality can be improved using ICU type information and by balancing the ’non-survivor’ class. The findings of the study may be useful for quantifying the quality of ICU care, managing ICU resources and selecting appropriate interventions.