Machine learning and convolutional neural networks for melanomas identification

Il machine learning negli ultimi anni ha acquisito una crescente popolarità nell’ambito della ricerca scientifica e delle sue applicazioni. Lo scopo di questa tesi è stato quello di studiare il machine learning nei suoi aspetti generali e applicarlo a problemi di computer vision. La tesi ha affrontato le difficoltà del dover spiegare dal punto di vista teorico gli algoritmi alla base delle reti neurali convoluzionali e ha successivamente trattato due problemi concreti di riconoscimento immagini: il dataset MNIST (immagini di cifre scritte a mano) e un dataset che sarà chiamato ”MELANOMA dataset” (immagini di melanomi e nevi sani). Utilizzando le tecniche spiegate nella sezione teorica si sono riusciti ad ottenere risultati soddifacenti per entrambi i dataset ottenendo una precisione del 98% per il MNIST e del 76.8% per il MELANOMA dataset

Implementazione di algoritmi Tiny Machine Learning per il monitoraggio strutturale basato su emissioni acustiche

Il monitoraggio basato su emissioni acustiche (AE) guidate si è confermato tra le tecniche più affidabili nel campo del Non-Destructive Testing delle strutture planari, vista anche la sua semplicità implementativa, i bassi costi che lo caratterizzano, la non invasività e la possibilità di realizzare un sistema che agisca in maniera continuativa ed in tempo reale sfruttando reti di sensori permanentemente installati, senza la necessità di ispezioni periodiche. In tale contesto, è possibile sfruttare l’abilità dell’apprendimento automatico nell’individuazione dei pattern nascosti all’interno dei segnali grezzi registrati, ottenendo così informazioni utili ai fini dell’applicazione considerata. L’esecuzione on-edge dei modelli, ovvero sul punto di acquisizione, consente di superare le limitazioni imposte dal processamento centralizzato dei dati, con notevoli vantaggi in termini di consumo energetico, tempestività nella risposta ed integrità degli stessi. A questo scopo, si rivela però necessario sviluppare modelli compatibili con le stringenti risorse hardware dei dispositivi a basso costo tipicamente impiegati. In questo elaborato verranno prese in esame alcune tipologie di reti neurali artificiali per l’estrazione dell’istante di arrivo (ToA) di un’emissione acustica all’interno di una sequenza temporale, in particolare quelle convoluzionali (CNNs) ed una loro variante più recente, le CapsNet basate su rounting by agreement. L’individuazione dei ToA relativi al medesimo evento su segnali acquisiti in diverse posizioni spaziali consente infatti di localizzare la sorgente da cui esso è scaturito. Le dimensioni di questi modelli permettono di eseguire l’inferenza direttamente su edge-device. I risultati ottenuti confermano la maggiore robustezza delle tecniche di apprendimento profondo rispetto ai metodi statistici tradizionali nel far fronte a diverse tipologie di disturbo, in particolare negli scenari più critici dal punto di vista del rapporto segnale-rumore.

Sviluppo di un sistema di climatizzazione automatico distribuito con l'utilizzo di tecniche di machine learning

Nella sede dell’azienda ospitante Alexide, si è ravvisata la mancanza di un sistema di controllo automatico da remoto dell’intero impianto di climatizzazione HVAC (Heating, Ventilation and Air Conditioning) utilizzato, e la soluzione migliore è risultata quella di attuare un processo di trasformazione della struttura in uno smart building. Ho quindi eseguito questa procedura di trasformazione digitale progettando e sviluppando un sistema distribuito in grado di gestire una serie di dati provenienti in tempo reale da sensori ambientali. L’architettura del sistema progettato è stata sviluppata in C# su ambiente dotNET, dove sono stati collezionati i dati necessari per il funzionamento del modello di predizione. Nella fattispecie sono stati utilizzati i dati provenienti dall’HVAC, da un sensore di temperatura interna dell'edificio e dal fotovoltaico installato nella struttura. La comunicazione tra il sistema distribuito e l’entità dell’HVAC avviene mediante il canale di comunicazione ModBus, mentre per quanto riguarda i dati della temperatura interna e del fotovoltaico questi vengono collezionati da sensori che inviano le informazioni sfruttando un canale di comunicazione che utilizza il protocollo MQTT, e lo stesso viene utilizzato come principale metodo di comunicazione all’interno del sistema, appoggiandosi ad un broker di messaggistica con modello publish/subscribe. L'automatizzazione del sistema è dovuta anche all'utilizzo di un modello di predizione con lo scopo di predire in maniera quanto più accurata possibile la temperatura interna all'edificio delle ore future. Per quanto riguarda il modello di predizione da me implementato e integrato nel sistema la scelta è stata quella di ispirarmi ad un modello ideato da Google nel 2014 ovvero il Sequence to Sequence. Il modello sviluppato si struttura come un encoder-decoder che utilizza le RNN, in particolare le reti LSTM.

Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifiers

The Support Vector (SV) machine is a novel type of learning machine, based on statistical learning theory, which contains polynomial classifiers, neural networks, and radial basis function (RBF) networks as special cases. In the RBF case, the SV algorithm automatically determines centers, weights and threshold such as to minimize an upper bound on the expected test error. The present study is devoted to an experimental comparison of these machines with a classical approach, where the centers are determined by $k$--means clustering and the weights are found using error backpropagation. We consider three machines, namely a classical RBF machine, an SV machine with Gaussian kernel, and a hybrid system with the centers determined by the SV method and the weights trained by error backpropagation. Our results show that on the US postal service database of handwritten digits, the SV machine achieves the highest test accuracy, followed by the hybrid approach. The SV approach is thus not only theoretically well--founded, but also superior in a practical application.

Un'analisi dell'impatto dell'informatica sul mercato del lavoro

In questa analisi si cercherà di comprendere cosa caratterizza questa l'ondata di progresso tecnologico che sta cambiando il mercato del lavoro. Il principale aspetto negativo di questo progresso si chiama "Technological Unemployment". Benché gli esperti si trovino in disaccordo su quali siano le cause della persistente alta disoccupazione, Brynjolfsson e McAfee puntano il dito contro l'automazione che ha soppiantato i lavori ripetitivi delle aziende. Tuttavia, è anche vero che il progresso ha sempre portato aumenti di produttività, e soprattutto nuovi tipi di occupazioni che hanno compensato la perdita di posti di lavoro, nel medio-lungo termine. Keynes evidenzia che la disoccupazione dovuta alla scoperta di strumenti economizzatori di manodopera procede con ritmo più rapido di quello con cui riusciamo a trovare nuovi impieghi per la manodopera stessa. Da ciò si crea ansia per il futuro, più o meno motivata. Gli stessi esperti sono spaccati a metà tra chi ha fiducia nei possibili risvolti positivi del progresso e chi invece teme possa comportare scenari catastrofici. Le macchine ci rubano lavoro o ci liberano da esso? Con questa ricerca ci si pone l'obiettivo di analizzare le effettive prospettive dei prossimi decenni. Nel capitolo 2 che è il corpo della tesi prenderemo soprattutto in conto il lavoro accademico di Frey ed Osborne dell'Oxford Martin School, intitolato "The future of employment: how susceptible are jobs to computerisation?" (2013). Essi sono stati tra i primi a studiare e quantificare cosa comporteranno le nuove tecnologie in termini di impiego. Il loro obiettivo era individuare le occupazioni a rischio, da qui a vent'anni, nel mercato del lavoro degli Stati Uniti e la relazione che intercorre tra la loro probabilità di essere computerizzati e i loro salari e livello d'istruzione medi, il tutto valutato attraverso l'ausilio di una nuova metodologia che si vedrà nel dettaglio. A conclusioni simili alle loro, per certi aspetti, è successivamente giunto anche Autor; tra l'altro viene spesso citato per altre sue opere dagli stessi Frey e Osborne, che usano le sue categorizzazioni per impostare la struttura del loro calcolo dell'automatizzabilità dei lavori utilizzando i recenti miglioramenti nelle scienze ingegneristiche quali ML (Machine Learning ad esempio Data mining, Machine vision, Computational statistics o più in generale AI) e MR (Mobile robotics) come strumenti di valutazione. Oltre alle sue ricerche, si presenteranno brevemente i risultati di un recente sondaggio tenuto dal Pew Research Center in cui importanti figure dell'informatica e dell'economia esprimono il loro giudizio sul futuro panorama del mondo del lavoro, considerando l'imminente ondata di innovazioni tecnologiche. La tesi si conclude con un'elaborazione personale. In questo modo si prenderà coscienza dei problemi concreti che il progresso tecnologico potrebbe procurare, ma anche dei suoi aspetti positivi.

Sequence and Structural Determinants of Specificity Differences between Paralogous Transcription Factors

Transcription factors (TFs) control the temporal and spatial expression of target genes by interacting with DNA in a sequence-specific manner. Recent advances in high throughput experiments that measure TF-DNA interactions in vitro and in vivo have facilitated the identification of DNA binding sites for thousands of TFs. However, it remains unclear how each individual TF achieves its specificity, especially in the case of paralogous TFs that recognize distinct target genomic sites despite sharing very similar DNA binding motifs. In my work, I used a combination of high throughput in vitro protein-DNA binding assays and machine-learning algorithms to characterize and model the binding specificity of 11 paralogous TFs from 4 distinct structural families. My work proves that even very closely related paralogous TFs, with indistinguishable DNA binding motifs, oftentimes exhibit differential binding specificity for their genomic target sites, especially for sites with moderate binding affinity. Importantly, the differences I identify in vitro and through computational modeling help explain, at least in part, the differential in vivo genomic targeting by paralogous TFs. Future work will focus on in vivo factors that might also be important for specificity differences between paralogous TFs, such as DNA methylation, interactions with protein cofactors, or the chromatin environment. In this larger context, my work emphasizes the importance of intrinsic DNA binding specificity in targeting of paralogous TFs to the genome.

Improving understandability in consumer health information search: Uevora @ 2016 fire chis

This paper presents our work at 2016 FIRE CHIS. Given a CHIS query and a document associated with that query, the task is to classify the sentences in the document as relevant to the query or not; and further classify the relevant sentences to be supporting, neutral or opposing to the claim made in the query. In this paper, we present two different approaches to do the classification. With the first approach, we implement two models to satisfy the task. We first implement an information retrieval model to retrieve the sentences that are relevant to the query; and then we use supervised learning method to train a classification model to classify the relevant sentences into support, oppose or neutral. With the second approach, we only use machine learning techniques to learn a model and classify the sentences into four classes (relevant & support, relevant & neutral, relevant & oppose, irrelevant & neutral). Our submission for CHIS uses the first approach.

Multitask learning of environmental spatial data

The present research deals with an application of artificial neural networks for multitask learning from spatial environmental data. The real case study (sediments contamination of Geneva Lake) consists of 8 pollutants. There are different relationships between these variables, from linear correlations to strong nonlinear dependencies. The main idea is to construct a subsets of pollutants which can be efficiently modeled together within the multitask framework. The proposed two-step approach is based on: 1) the criterion of nonlinear predictability of each variable ?k? by analyzing all possible models composed from the rest of the variables by using a General Regression Neural Network (GRNN) as a model; 2) a multitask learning of the best model using multilayer perceptron and spatial predictions. The results of the study are analyzed using both machine learning and geostatistical tools.

PDM 2006: Proceedings of the International Workshop on Data Mining

Recently major processor manufacturers have announced a dramatic shift in their paradigm to increase computing power over the coming years. Instead of focusing on faster clock speeds and more powerful single core CPUs, the trend clearly goes towards multi core systems. This will also result in a paradigm shift for the development of algorithms for computationally expensive tasks, such as data mining applications. Obviously, work on parallel algorithms is not new per se but concentrated efforts in the many application domains are still missing. Multi-core systems, but also clusters of workstations and even large-scale distributed computing infrastructures provide new opportunities and pose new challenges for the design of parallel and distributed algorithms. Since data mining and machine learning systems rely on high performance computing systems, research on the corresponding algorithms must be on the forefront of parallel algorithm research in order to keep pushing data mining and machine learning applications to be more powerful and, especially for the former, interactive. To bring together researchers and practitioners working in this exciting field, a workshop on parallel data mining was organized as part of PKDD/ECML 2006 (Berlin, Germany). The six contributions selected for the program describe various aspects of data mining and machine learning approaches featuring low to high degrees of parallelism: The first contribution focuses the classic problem of distributed association rule mining and focuses on communication efficiency to improve the state of the art. After this a parallelization technique for speeding up decision tree construction by means of thread-level parallelism for shared memory systems is presented. The next paper discusses the design of a parallel approach for dis- tributed memory systems of the frequent subgraphs mining problem. This approach is based on a hierarchical communication topology to solve issues related to multi-domain computational envi- ronments. The forth paper describes the combined use and the customization of software packages to facilitate a top down parallelism in the tuning of Support Vector Machines (SVM) and the next contribution presents an interesting idea concerning parallel training of Conditional Random Fields (CRFs) and motivates their use in labeling sequential data. The last contribution finally focuses on very efficient feature selection. It describes a parallel algorithm for feature selection from random subsets. Selecting the papers included in this volume would not have been possible without the help of an international Program Committee that has provided detailed reviews for each paper. We would like to also thank Matthew Otey who helped with publicity for the workshop.

Particle competition and cooperation to prevent error propagation from mislabeled data in semi-supervised learning

Semi-supervised learning is applied to classification problems where only a small portion of the data items is labeled. In these cases, the reliability of the labels is a crucial factor, because mislabeled items may propagate wrong labels to a large portion or even the entire data set. This paper aims to address this problem by presenting a graph-based (network-based) semi-supervised learning method, specifically designed to handle data sets with mislabeled samples. The method uses teams of walking particles, with competitive and cooperative behavior, for label propagation in the network constructed from the input data set. The proposed model is nature-inspired and it incorporates some features to make it robust to a considerable amount of mislabeled data items. Computer simulations show the performance of the method in the presence of different percentage of mislabeled data, in networks of different sizes and average node degree. Importantly, these simulations reveals the existence of the critical points of the mislabeled subset size, below which the network is free of wrong label contamination, but above which the mislabeled samples start to propagate their labels to the rest of the network. Moreover, numerical comparisons have been made among the proposed method and other representative graph-based semi-supervised learning methods using both artificial and real-world data sets. Interestingly, the proposed method has increasing better performance than the others as the percentage of mislabeled samples is getting larger. © 2012 IEEE.

Extreme learning machine for predicting HLA-peptide binding

Machine learning techniques have been recognized as powerful tools for learning from data. One of the most popular learning techniques, the Back-Propagation (BP) Artificial Neural Networks, can be used as a computer model to predict peptides binding to the Human Leukocyte Antigens (HLA). The major advantage of computational screening is that it reduces the number of wet-lab experiments that need to be performed, significantly reducing the cost and time. A recently developed method, Extreme Learning Machine (ELM), which has superior properties over BP has been investigated to accomplish such tasks. In our work, we found that the ELM is as good as, if not better than, the BP in term of time complexity, accuracy deviations across experiments, and most importantly - prevention from over-fitting for prediction of peptide binding to HLA.

Learning Data-Driven Models of Non-Verbal Behaviors for Building Rapport Using an Intelligent Virtual Agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness. Evidence-based patient-centered Brief Motivational Interviewing (BMI) interven- tions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary. Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems. To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].

New Advancements of Scalable Statistical Methods for Learning Latent Structures in Big Data

Constant technology advances have caused data explosion in recent years. Accord- ingly modern statistical and machine learning methods must be adapted to deal with complex and heterogeneous data types. This phenomenon is particularly true for an- alyzing biological data. For example DNA sequence data can be viewed as categorical variables with each nucleotide taking four different categories. The gene expression data, depending on the quantitative technology, could be continuous numbers or counts. With the advancement of high-throughput technology, the abundance of such data becomes unprecedentedly rich. Therefore efficient statistical approaches are crucial in this big data era.

Previous statistical methods for big data often aim to find low dimensional struc- tures in the observed data. For example in a factor analysis model a latent Gaussian distributed multivariate vector is assumed. With this assumption a factor model produces a low rank estimation of the covariance of the observed variables. Another example is the latent Dirichlet allocation model for documents. The mixture pro- portions of topics, represented by a Dirichlet distributed variable, is assumed. This dissertation proposes several novel extensions to the previous statistical methods that are developed to address challenges in big data. Those novel methods are applied in multiple real world applications including construction of condition specific gene co-expression networks, estimating shared topics among newsgroups, analysis of pro- moter sequences, analysis of political-economics risk data and estimating population structure from genotype data.

Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as f-test is performed during each node’s split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.

End-to-end Deep Metric Learning con Vision-Language Model per il Fashion Image Captioning

L'image captioning è un task di machine learning che consiste nella generazione di una didascalia, o caption, che descriva le caratteristiche di un'immagine data in input. Questo può essere applicato, ad esempio, per descrivere in dettaglio i prodotti in vendita su un sito di e-commerce, migliorando l'accessibilità del sito web e permettendo un acquisto più consapevole ai clienti con difficoltà visive. La generazione di descrizioni accurate per gli articoli di moda online è importante non solo per migliorare le esperienze di acquisto dei clienti, ma anche per aumentare le vendite online. Oltre alla necessità di presentare correttamente gli attributi degli articoli, infatti, descrivere i propri prodotti con il giusto linguaggio può contribuire a catturare l'attenzione dei clienti. In questa tesi, ci poniamo l'obiettivo di sviluppare un sistema in grado di generare una caption che descriva in modo dettagliato l'immagine di un prodotto dell'industria della moda dato in input, sia esso un capo di vestiario o un qualche tipo di accessorio. A questo proposito, negli ultimi anni molti studi hanno proposto soluzioni basate su reti convoluzionali e LSTM. In questo progetto proponiamo invece un'architettura encoder-decoder, che utilizza il modello Vision Transformer per la codifica delle immagini e GPT-2 per la generazione dei testi. Studiamo inoltre come tecniche di deep metric learning applicate in end-to-end durante l'addestramento influenzino le metriche e la qualità delle caption generate dal nostro modello.