To see the other types of publications on this topic, follow the link: Python for Machine Language (ML).
Dissertations / Theses on the topic 'Python for Machine Language (ML)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 24 dissertations / theses for your research on the topic 'Python for Machine Language (ML).'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Conti, Matteo. "Machine Learning Based Programming Language Identification." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20875/.
Full textAbstract:
L'avvento dell'era digitale ha contribuito allo sviluppo di nuovi settori tecnologici, i quali, per diretta conseguenza, hanno portato alla richiesta di nuove figure professionali capaci di assumere un ruolo chiave nel processo d'innovazione tecnologica. L'aumento di questa richiesta ha interessato particolarmente il settore dello sviluppo del software, a seguito della nascita di nuovi linguaggi di programmazione e nuovi campi a cui applicarli. La componente principale di cui è composto un software, infatti, è il codice sorgente, il quale può essere rappresentato come un archivio di uno o più file testuali contenti una serie d'istruzioni scritte in uno o più linguaggi di programmazione. Nonostante molti di questi vengano utilizzati in diversi settori tecnologici, spesso accade che due o più di questi condividano una struttura sintattica e semantica molto simile. Chiaramente questo aspetto può generare confusione nell'identificazione di questo all'interno di un frammento di codice, soprattutto se consideriamo l'eventualità che non sia specificata nemmeno l'estensione dello stesso file. Infatti, ad oggi, la maggior parte del codice disponibile online contiene informazioni relative al linguaggio di programmazione specificate manualmente. All'interno di questo elaborato ci concentreremo nel dimostrare che l'identificazione del linguaggio di programmazione di un file `generico' di codice sorgente può essere effettuata in modo automatico utilizzando algoritmi di Machine Learning e non usando nessun tipo di assunzione `a priori' sull'estensione o informazioni particolari che non riguardino il contenuto del file. Questo progetto segue la linea dettata da alcune ricerche precedenti basate sullo stesso approccio, confrontando tecniche di estrazione delle features differenti e algoritmi di classificazione con caratteristiche molto diverse, cercando di ottimizzare la fase di estrazione delle features in base al modello considerato.
2
Wallner, Vanja. "Mapping medical expressions to MedDRA using Natural Language Processing." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-426916.
Full textAbstract:
Pharmacovigilance, also referred to as drug safety, is an important science for identifying risks related to medicine intake. Side effects of medicine can be caused by for example interactions, high dosage and misuse. In order to find patterns in what causes the unwanted effects, information needs to be gathered and mapped to predefined terms. This mapping is today done manually by experts which can be a very difficult and time consuming task. In this thesis the aim is to automate the process of mapping side effects by using machine learning techniques. The model was developed using information from preexisting mappings of verbatim expressions of side effects. The final model that was constructed made use of the pre-trained language model BERT, which has received state-of-the-art results within the NLP field. When evaluating on the test set the final model performed an accuracy of 80.21%. It was found that some verbatims were very difficult for our model to classify mainly because of ambiguity or lack of information contained in the verbatim. As it is very important for the mappings to be done correctly, a threshold was introduced which left for manual mapping the verbatims that were most difficult to classify. This process could however still be improved as suggested terms were generated from the model, which could be used as support for the specialist responsible for the manual mapping.
3
Björkman, Desireé. "Machine Learning Evaluation of Natural Language to Computational Thinking : On the possibilities of coding without syntax." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-424269.
Full textAbstract:
Voice commands are used in today's society to offer services like putting events into a calendar, tell you about the weather and to control the lights at home. This project tries to extend the possibilities of voice commands by improving an earlier proof of concept system that interprets intention given in natural language to program code. This improvement was made by mixing linguistic methods and neural networks to increase accuracy and flexibility of the interpretation of input. A user testing phase was made to conclude if the improvement would attract users to the interface. The results showed possibilities of educational purposes for computational thinking and the issues to overcome to become a general programming tool.
4
Scaglione, Emanuel. "BlenderBot 2.0: Studio e Modellazione di un Chatbot basato su Transformers." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Find full textAbstract:
I Transformers hanno raggiunto lo stato dell’arte in qualsiasi ambito del Natural Language Processing (NLP) e del Natural Language Understanding (NLU), in questo lavoro di tesi è stata studiata l’architettura originale e alcune delle migliorie apportate a questa nel corso degli ultimi anni.
In una seconda fase è stato studiato un Chat Bot rivoluzionario reso pubblico nel Luglio del 2021, chiamato Blender Bot 2.0. Questo bot di Facebook è sia capace di sfruttare una memoria a lungo termine facilmente estendibile e sostituibile per immagazzinare informazioni sui propri interlocutori e sul mondo esterno, sia di effettuare ricerche online quando posto di fronte a quesiti di cui non è sicuro di conoscere la risposta. Il tutto è stato osservato non solo in termini di qualità dei risultati generati dai modelli, ma anche da un punto di vista di risorse impiegate. L’obiettivo è stato quello di minimizzare il consumo di memoria e il tempo necessario per addestrare i modelli, in modo da poter rendere accessibili le loro abilità su larga scala anche in presenza di hardware economici, diminuendo conseguentemente i costi per chiunque voglia farci affidamento; un grande passo per singoli individui appassionati, ma soprattutto per aziende interessate ad impiegarli in un contesto produttivo.
5
Gennari, Riccardo. "End-to-end Deep Metric Learning con Vision-Language Model per il Fashion Image Captioning." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2022. http://amslaurea.unibo.it/25772/.
Full textAbstract:
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.
6
Rasocha, David. "Návrh řídicího systému pro malý zkušební stroj." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2020. http://www.nusl.cz/ntk/nusl-417777.
Full textAbstract:
This thesis focuses on design of small testing machine for measuring tensile strength of materials. Appropriate hardware for driving the motor with serial communication will be used. Main drive is a stepper motor with microstepping. Instructions for motor is provided by microcontroler which will be comunicating with aplication in computer. This aplication will have all user functions nessesary for using this device.
7
Montalti, Giacomo. "Identificazione di farmaci e dispositivi medici equivalenti con tecniche di natural language processing e deep learning." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16828/.
Full textAbstract:
Il deep learning è un campo relativamente giovane le cui potenzialità sono ancora tutte da esplorare, in grado di elaborare in maniera ancora più approfondita i dati, e sarà affrontato nel dettaglio all'interno di questo lavoro di tesi.
Questa tecnologia ha permesso di migliorare drasticamente i risultati raggiunti in passato in tantissimi settori, consentendo ad esempio lo sviluppo di auto a guida autonoma, assistenti virtuali in grado di comprendere una conversazione e di fornire risposte alle nostre domande o macchinari medicali capaci di identificare masse tumorali con una precisione maggiore rispetto a quella umana.
All'interno di questo elaborato verranno analizzati e sperimentati diversi approcci recenti in ambito natural language processing (NLP) e deep learning (DL), allo scopo di identificare prodotti medicali equivalenti dalla loro breve descrizione testuale destrutturata.
8
Lat, Radek. "Nástroj pro automatické kategorizování webových stránek." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2014. http://www.nusl.cz/ntk/nusl-236054.
Full textAbstract:
Tato diplomová práce popisuje návrh a implementaci nástroje pro automatickou kategorizaci webových stránek. Cílem nástroje je aby byl schopen se z ukázkových webových stránek naučit, jak každá kategorie vypadá. Poté by měl nástroj zvládnout přiřadit naučené kategorie k dříve nespatřeným webovým stránkám. Nástroj by měl podporovat více kategorií a jazyků. Pro vývoj nástroje byly použity pokročilé techniky strojového učení, detekce jazyků a dolování dat. Nástroj je založen na open source knihovnách a je napsán v jazyce Python 3.3.
9
Keisala, Simon. "Using a Character-Based Language Model for Caption Generation." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-163001.
Full textAbstract:
Using AI to automatically describe images is a challenging task. The aim of this study has been to compare the use of character-based language models with one of the current state-of-the-art token-based language models, im2txt, to generate image captions, with focus on morphological correctness. Previous work has shown that character-based language models are able to outperform token-based language models in morphologically rich languages. Other studies show that simple multi-layered LSTM-blocks are able to learn to replicate the syntax of its training data. To study the usability of character-based language models an alternative model based on TensorFlow im2txt has been created. The model changes the token-generation architecture into handling character-sized tokens instead of word-sized tokens. The results suggest that a character-based language model could outperform the current token-based language models, although due to time and computing power constraints this study fails to draw a clear conclusion. A problem with one of the methods, subsampling, is discussed. When using the original method on character-sized tokens this method removes characters (including special characters) instead of full words. To solve this issue, a two-phase approach is suggested, where training data first is separated into word-sized tokens where subsampling is performed. The remaining tokens are then separated into character-sized tokens. Future work where the modified subsampling and fine-tuning of the hyperparameters are performed is suggested to gain a clearer conclusion of the performance of character-based language models.
10
Borghesi, Andrea. "Topic Analysis della letteratura scientifica sul tema Computer Chess con Metodi di Text Mining Non Supervisionati." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24252/.
Full textAbstract:
Progettazione e implementazione di modelli di text mining non supervisionati su un dataset di dati non strutturati: articoli sulla storia del computer chess. Si sono affrontati per cui argomenti legati al Natural Language Processing (NLP). Inoltre, sono state affrontate tecniche di text augmentation per provvedere al bilanciamento delle classi del dataset. Tra i modelli utilizzati sono presenti: LDA, Word Embeddings, algoritmi di Clustering e Transformers.
11
Pantieri, Andrea. "Citizen science per le scuole: sviluppo di un’app mobile per supportare la classificazione delle piante." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24241/.
Full textAbstract:
Sul web e negli store sono presenti diverse applicazioni che trattano la tematica ambientale nei termini di sostenibilità ed educazione, tese a promuovere azioni positive e a sensibilizzare gli utenti sull’argomento. Nello specifico, l’app sviluppata ha l’obiettivo di supportare la classificazione delle piante, come elemento della biodiversità, attraverso un approccio di gamification e tecniche di mobile computing per rendere l’applicazione accessibile ed usabile sui dispositivi mobile. Il cuore del progetto è quindi incentrato sul riconoscimento della flora grazie ad un sistema premiante di quiz con domande a risposta singola. Sono presenti elementi comuni di gioco come l’attribuzione di punti, il posizionamento in una classifica e la condivisione dei risultati. In aggiunta al mobile computing e alla gamification, è stato sviluppato un modello di Machine Learning (ML) in grado di apprendere da un insieme di dati certi di input e di classificare le immagini nelle categorie di flora presenti, garantendo la correttezza delle risposte al quiz in comparazione a quelle dell’utente. Nello progettazione e sviluppo dell’app, sono stati utilizzati il linguaggio di programmazione React Native (framework di Javascript) e la relativa piattaforma open-source Expo con le loro librerie. Per l’implementazione del modello di ML, si è fatto invece riferimento al linguaggio di programmazione Python e alle API di TensorFlow, in particolare Keras. La fase vera e propria di sviluppo ha riguardato la progettazione di mockup per il design, la ricerca e raccolta dei contenuti e l’implementazione del codice e del modello di ML.
12
Giuliani, Luca. "Extending the Moving Targets Method for Injecting Constraints in Machine Learning." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23885/.
Full textAbstract:
Informed Machine Learning is an umbrella term that comprises a set of methodologies in which domain knowledge is injected into a data-driven system in order to improve its level of accuracy, satisfy some external constraint, and in general serve the purposes of explainability and reliability. The said topid has been widely explored in the literature by means of many different techniques. Moving Targets is one such a technique particularly focused on constraint satisfaction: it is based on decomposition and bi-level optimization and proceeds by iteratively refining the target labels through a master step which is in charge of enforcing the constraints, while the training phase is delegated to a learner. In this work, we extend the algorithm in order to deal with semi-supervised learning and soft constraints. In particular, we focus our empirical evaluation on both regression and classification tasks involving monotonicity shape constraints. We demonstrate that our method is robust with respect to its hyperparameters, as well as being able to generalize very well while reducing the number of violations on the enforced constraints. Additionally, the method can even outperform, both in terms of accuracy and constraint satisfaction, other state-of-the-art techniques such as Lattice Models and Semantic-based Regularization with a Lagrangian Dual approach for automatic hyperparameter tuning.
13
Daneshvar, Saman. "User Modeling in Social Media: Gender and Age Detection." Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39535.
Full textAbstract:
Author profiling is a field within Natural Language Processing (NLP) that is concerned with identifying various characteristics and demographic factors of authors, such as gender, age, location, native language, political orientation, and personality by analyzing the style and content of their writings. There is a growing interest in author profiling, with applications in marketing and advertising, opinion mining, personalization, recommendation systems, forensics, security, and defense.
In this work, we build several classification models using NLP, Deep Learning, and classical Machine Learning techniques that can identify the gender and age of a Twitter user based on the textual contents of their correspondence (tweets) on the platform.
Our SVM gender classifier utilizes a combination of word and character n-grams as features, dimensionality reduction using Latent Semantic Analysis (LSA), and a Support Vector Machine (SVM) classifier with linear kernel. At the PAN 2018 author profiling shared task, this model achieved the highest performance with 82.21%, 82.00%, and 80.90% accuracy on the English, Spanish, and Arabic datasets, respectively. Our age classifier was trained on a dataset of 11,160 Twitter users, using the same approach, though the age classification experiments are preliminary.
Our Deep Learning gender classifiers are trained and tested on English datasets. Our feedforward neural network consisting of a word embedding layer, flattening, and two densely-connected layers achieves 79.57% accuracy, and our bidirectional Long Short-Term Memory (LSTM) neural network achieves 76.85% accuracy on the gender classification task.
14
Dahl, Jonas. "Feature Selection for Sentiment Analysis of Swedish News Article Titles." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233534.
Full textAbstract:
The aim of this study was to elaborate the possibilities of sentiment analyzing Swedish news article titles using machine learning approaches and find how the text is best represented in such conditions. Sentiment analysis has traditionally been conducted by part-of-speech tagging and counting word polarities, which performs well for large domains and in absence of large sets of training data. For narrower domains and previously labeled data, supervised learning can be used. The work of this thesis tested the performance of a convolutional neural network and a Support Vector Machine on different sets of data. The data sets were constructed to represent various language features. This included for example a simple unigram bag-of-words model storing word counts, a bigram bag-of-words model to include the ordering of words and an integer vector summary of the title. The study concluded that each of the tested feature sets gave information about the sentiment to various extents. The neural network approach with all feature sets combined performed better than the two annotators of the study. Despite the limited data set, overfitting did not seem to be a problem when using the features together.<br>Målet med detta arbete var att undersöka möjligheten till sentimentanalys av svenska nyhetsrubriker med hjälp av maskininlärning och förstå hur dessa rubriker bäst representeras. Sentimentanalys har traditionellt använt ordklassmärkning och räknande av ordpolariteter, som fungerar bra för stora domäner där avsaknaden av större uppmärkt träningsdata är stor. För mindre domäner och tidigare uppmärkt data kan övervakat lärande användas. Inom ramen för detta arbete undersöktes ett artificiellt neuronnät med faltning och en stödvektormaskin på olika datamängder. Datamängderna formades för att representera olika språkegenskaper. Detta inkluderade bland annat en enkel ordräkningsmodell, en bigramräkningsmodell och en heltalssummering av generella egenskaper för rubriken. I studien dras slutsatsen att varje datamängd innebar att ny information kunde tillföras i olika stor utsträckning. Det artificiella neuronnätet med alla datamängder tillsammans presterade bättre än de två personer som märkte upp data till denna studie. Trots en begränsad datamängd inträffade verkade inte modellerna övertränas.
15
Benatti, Mattia. "Progettazione e Sviluppo di una Piattaforma Multi-Sorgente per l’Ottimizzazione dei Servizi di Emergenza." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Find full textAbstract:
L'elaborato di tesi descriverà il progetto di tirocinio svolto presso l'azienda EBWorld S.R.L. di Bologna. Le richieste di questa attività prevedevano di sviluppare un prodotto che fosse in grado di raccogliere dati ed informazioni di diverso tipo da più sorgenti differenti; il contesto di tali informazioni doveva riguardare gli eventi di pericolo. L'obiettivo principale era quello di fornire un monitoraggio in tempo reale di questo tipo di situazioni, così da rendere più efficiente la gestione dei servizi di emergenza. Le sorgenti provengono dall'ambito Social Network (Twitter), da organi di informazione ufficiale (Feed RSS di quotidiani online), da sensoristica e servizi pubblici che operano a livello nazionale (web service di INGV per monitoraggio di eventi sismici). Tutti questi dati vengono raccolti e memorizzati all'interno di un database PostGIS. Per le notizie in formato testuale, è stato implementato anche un modello di Machine Learning per il Natural Language Processing, il quale deve determinare se la notizia fa riferimento a un pericolo reale. Tutta la parte di back-end viene caricata sul server aziendale mediante il servizio Docker. L'andamento degli eventi verrà seguito visivamente su un'interfaccia web, dove le informazioni potranno essere raggruppate in base al tipo fonte, la quale rappresenterà anche un layer della mappa, e potranno essere filtrate in base all'area geografica, parole e altro. Per l'architettura del back-end si è scelto di utilizzare l'Observer pattern, dove i crawler rappresentano i Subject mentre gli Observer gestiscono le funzioni per l'inserimento dei record nelle rispettive tabelle del database ed eventualmente la discriminazione dell'informazione tramite l'algoritmo di ML. Infine, è stata effettuata una fase di validazione delle diverse componenti, con particolare attenzione rispetto ai risultati ottenuti dal modello di ML sviluppato.
16
Appelstål, Michael. "Multimodal Model for Construction Site Aversion Classification." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-421011.
Full textAbstract:
Aversion on construction sites can be everything from missingmaterial, fire hazards, or insufficient cleaning. These aversionsappear very often on construction sites and the construction companyneeds to report and take care of them in order for the site to runcorrectly. The reports consist of an image of the aversion and atext describing the aversion. Report categorization is currentlydone manually which is both time and cost-ineffective. The task for this thesis was to implement and evaluate an automaticmultimodal machine learning classifier for the reported aversionsthat utilized both the image and text data from the reports. Themodel presented is a late-fusion model consisting of a Swedish BERTtext classifier and a VGG16 for image classification. The results showed that an automated classifier is feasible for thistask and could be used in real life to make the classification taskmore time and cost-efficient. The model scored a 66.2% accuracy and89.7% top-5 accuracy on the task and the experiments revealed someareas of improvement on the data and model that could be furtherexplored to potentially improve the performance.
17
Razavi, Amir Hossein. "Automatic Text Ontological Representation and Classification via Fundamental to Specific Conceptual Elements (TOR-FUSE)." Thèse, Université d'Ottawa / University of Ottawa, 2012. http://hdl.handle.net/10393/23061.
Full textAbstract:
In this dissertation, we introduce a novel text representation method mainly used for text classification purpose. The presented representation method is initially based on a variety of closeness relationships between pairs of words in text passages within the entire corpus. This representation is then used as the basis for our multi-level lightweight ontological representation method (TOR-FUSE), in which documents are represented based on their contexts and the goal of the learning task. The method is unlike the traditional representation methods, in which all the documents are represented solely based on the constituent words of the documents, and are totally isolated from the goal that they are represented for. We believe choosing the correct granularity of representation features is an important aspect of text classification. Interpreting data in a more general dimensional space, with fewer dimensions, can convey more discriminative knowledge and decrease the level of learning perplexity. The multi-level model allows data interpretation in a more conceptual space, rather than only containing scattered words occurring in texts. It aims to perform the extraction of the knowledge tailored for the classification task by automatic creation of a lightweight ontological hierarchy of representations. In the last step, we will train a tailored ensemble learner over a stack of representations at different conceptual granularities. The final result is a mapping and a weighting of the targeted concept of the original learning task, over a stack of representations and granular conceptual elements of its different levels (hierarchical mapping instead of linear mapping over a vector). Finally the entire algorithm is applied to a variety of general text classification tasks, and the performance is evaluated in comparison with well-known algorithms.
18
Talevi, Luca, and Luca Talevi. "“Decodifica di intenzioni di movimento dalla corteccia parietale posteriore di macaco attraverso il paradigma Deep Learning”." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17846/.
Full textAbstract:
Le Brain Computer Interfaces (BCI) invasive permettono di restituire la mobilità a pazienti che hanno perso il controllo degli arti: ciò avviene attraverso la decodifica di segnali bioelettrici prelevati da aree corticali di interesse al fine di guidare un arto prostetico. La decodifica dei segnali neurali è quindi un punto critico nelle BCI, richiedendo lo sviluppo di algoritmi performanti, affidabili e robusti.
Tali requisiti sono soddisfatti in numerosi campi dalle Deep Neural Networks, algoritmi adattivi le cui performance scalano con la quantità di dati forniti, allineandosi con il crescente numero di elettrodi degli impianti.
Impiegando segnali pre-registrati dalla corteccia di due macachi durante movimenti di reach-to-grasp verso 5 oggetti differenti, ho testato tre basilari esempi notevoli di DNN – una rete densa multistrato, una Convolutional Neural Network (CNN) ed una Recurrent NN (RNN) – nel compito di discriminare in maniera continua e real-time l’intenzione di movimento verso ciascun oggetto. In particolare, è stata testata la capacità di ciascun modello di decodificare una generica intenzione (single-class), la performance della migliore rete risultante nel discriminarle (multi-class) con o senza metodi di ensemble learning e la sua risposta ad un degrado del segnale in ingresso. Per agevolarne il confronto, ciascuna rete è stata costruita e sottoposta a ricerca iperparametrica seguendo criteri comuni.
L’architettura CNN ha ottenuto risultati particolarmente interessanti, ottenendo F-Score superiori a 0.6 ed AUC superiori a 0.9 nel caso single-class con metà dei parametri delle altre reti e tuttavia maggior robustezza. Ha inoltre mostrato una relazione quasi-lineare con il degrado del segnale, priva di crolli prestazionali imprevedibili.
Le DNN impiegate si sono rivelate performanti e robuste malgrado la semplicità, rendendo eventuali architetture progettate ad-hoc promettenti nello stabilire un nuovo stato dell’arte nel controllo neuroprotesico.
19
Zanghieri, Marcello. "sEMG-based hand gesture recognition with deep learning." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18112/.
Full textAbstract:
Hand gesture recognition based on surface electromyographic (sEMG) signals is a promising approach for the development of Human-Machine Interfaces (HMIs) with a natural control, such as intuitive robot interfaces or poly-articulated prostheses. However, real-world applications are limited by reliability problems due to motion artifacts, postural and temporal variability, and sensor re-positioning.
This master thesis is the first application of deep learning on the Unibo-INAIL dataset, the first public sEMG dataset exploring the variability between subjects, sessions and arm postures, by collecting data over 8 sessions of each of 7 able-bodied subjects executing 6 hand gestures in 4 arm postures. In the most recent studies, the variability is addressed with training strategies based on training set composition, which improve inter-posture and inter-day generalization of classical (i.e. non-deep) machine learning classifiers, among which the RBF-kernel SVM yields the highest accuracy.
The deep architecture realized in this work is a 1d-CNN implemented in Pytorch, inspired by a 2d-CNN reported to perform well on other public benchmark databases. On this 1d-CNN, various training strategies based on training set composition were implemented and tested.
Multi-session training proves to yield higher inter-session validation accuracies than single-session training. Two-posture training proves to be the best postural training (proving the benefit of training on more than one posture), and yields 81.2% inter-posture test accuracy. Five-day training proves to be the best multi-day training, and yields 75.9% inter-day test accuracy. All results are close to the baseline. Moreover, the results of multi-day trainings highlight the phenomenon of user adaptation, indicating that training should also prioritize recent data.
Though not better than the baseline, the achieved classification accuracies rightfully place the 1d-CNN among the candidates for further research.
20
Bergkvist, Alexander, Nils Hedberg, Sebastian Rollino, and Markus Sagen. "Surmize: An Online NLP System for Close-Domain Question-Answering and Summarization." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-412247.
Full textAbstract:
The amount of data available and consumed by people globally is growing. To reduce mental fatigue and increase the general ability to gain insight into complex texts or documents, we have developed an application to aid in this task. The application allows users to upload documents and ask domain-specific questions about them using our web application. A summarized version of each document is presented to the user, which could further facilitate their understanding of the document and guide them towards what types of questions could be relevant to ask. Our application allows users flexibility with the types of documents that can be processed, it is publicly available, stores no user data, and uses state-of-the-art models for its summaries and answers. The result is an application that yields near human-level intuition for answering questions in certain isolated cases, such as Wikipedia and news articles, as well as some scientific texts. The application shows a decrease in reliability and its prediction as to the complexity of the subject, the number of words in the document, and grammatical inconsistency in the questions increases. These are all aspects that can be improved further if used in production.<br>Mängden data som är tillgänglig och konsumeras av människor växer globalt. För att minska den mentala trötthet och öka den allmänna förmågan att få insikt i komplexa, massiva texter eller dokument, har vi utvecklat en applikation för att bistå i de uppgifterna. Applikationen tillåter användare att ladda upp dokument och fråga kontextspecifika frågor via vår webbapplikation. En sammanfattad version av varje dokument presenteras till användaren, vilket kan ytterligare förenkla förståelsen av ett dokument och vägleda dem mot vad som kan vara relevanta frågor att ställa. Vår applikation ger användare möjligheten att behandla olika typer av dokument, är tillgänglig för alla, sparar ingen personlig data, och använder de senaste modellerna inom språkbehandling för dess sammanfattningar och svar. Resultatet är en applikation som når en nära mänsklig intuition för vissa domäner och frågor, som exempelvis Wikipedia- och nyhetsartiklar, samt viss vetensaplig text. Noterade undantag för tillämpningen härrör från ämnets komplexitet, grammatiska korrekthet för frågorna och dokumentets längd. Dessa är områden som kan förbättras ytterligare om den används i produktionen.
21
Rohovets, Taras. "Machine learning algorithms to predict stocks movements with Python language and dedicated libraries." Master's thesis, 2019. http://hdl.handle.net/10400.26/30163.
Full textAbstract:
This research work focuses on machine learning algorithms in order to make predictions in financial markets. The foremost objective is to test whether the two machine learning algorithms: SVM and LSTM are capable of predicting the price movement in different time-frames and then develop a comparison analysis. In this research work, it is applied supervised machine learning with different input features. The practical and software component of this thesis applies Python programming language to test the hypothesis and act as proof of concept. The financial data quotes were obtained through online financial databases. The results demonstrate that SVM is capable of predicting the direction of the price while the LSTM did not present reliable results.
22
Kaur, Rajvir. "A comparative analysis of selected set of natural language processing (NLP) and machine learning (ML) algorithms for clinical coding using clinical classification standards." Thesis, 2018. http://hdl.handle.net/1959.7/uws:49614.
Full textAbstract:
In Australia, hospital discharge summaries created at the end of an episode of care contain patient information such as demographic data, medical history, various diagnosis, interventions carried out, medications and drug therapies provided to the patient. These discharge summaries not only serve as a record of the episode of care, but later converted into a set of clinical codes for statistical analysis purposes. The process of clinical coding refers to assigning alphanumeric codes to discharge summaries. In Australia, clinical coding is done using International Classification of Diseases, version 10, Australian Modification (ICD-10-AM) and Australian Classification of Health Interventions (ACHI) as per the Australian Coding Standards (ACS), in an acute and subacute care setting, in both public and private hospitals. Clinical coding and subsequent analysis facilitate funding, insurance claims processing and research. The task of assigning codes to an episode of care is a manual process. This posed challenges in terms of ever-increasing set of codes in ICD-10-AM and ACHI, changing coding standards in ACS, complexity of care episodes, and large training and recruitment costs associated with clinical coders. In addition, the manual clinical coding process is time consuming and prone to errors, leading to financial losses. The use of Natural Language Processing (NLP) and Machine Learning (ML) techniques is considered as a solution to the above problem. In this thesis, four different approaches namely, pattern matching, rule based, machine learning and hybrid technique are compared to identify most efficient algorithm suitable for clinical coding. The ICD-10-AM and ACHI consists of 22 chapters based on human body organs, where each chapter describe diseases and interventions of a body system. The aforementioned, NLP and ML comparison is carried out only two chapters namely, diseases of the respiratory system and diseases of the digestive system. Initially, the dataset contained 190 clinical records of two chapters and named as Data190. Due to the limited number of clinical records, another 45 records were added to the existing dataset and this resultant dataset was named as Data235. The clinical records were cleaned up in the pre-processing stage to extract useful information which includes principal diagnosis, additional diagnosis, diabetes condition, principal procedure, additional procedure and anaesthesia details. In data pre-processing, various NLP techniques such as tokenisation, stop word removal, spelling error detection and correction, negation detection and abbreviation expansion were applied. In pattern matching approach, the textstring were matched charcter by character against the ICD-10-AMand ACHI coding guide using regular expression. If the match was found, codes were assigned. Whereas, in rule-based, 409 rules were defined to avoid coding of wrong patterns. In machine learning, once the unwanted information was removed from the clinical records, text was represented in vector form for feature extraction using Bag of words (BoW) representation (Manning, Raghavan, & Schütze, 2008, p. 117) and Term Frequency-Inverse Document Frequency (TF-IDF) vectoriser (Manning et al., 2008, p. 118). After feature extraction, classification is done using seven classifiers namely Support Vector Machine (SVM) (Cortes & Vapnik, 1995), Naïve Bayes (Manning et al., 2008, p. 258), Decision Tree (Kumar, Assistant, & Sahni, 2011), Random Forest (Breiman, 2001), AdaBoost (Freund & Schapire, 1999), Multi Layer Perceptron (MLP) (Naraei, Abhari, & Sadeghian, 2016) and k-Nearest Neighbour (kNN) (Manning et al., 2008, p. 297). A set of standard metrics: Precision(P), Recall (R), F-score (F-score), Accuracy, Hamming Loss(HL) and Jaccard Similarity (JS) (Dalianis, 2018), (Aldrees & Chikh, 2016) is used to do the measure the efficiency of the said NLP and ML algorithms using the above mentioned two datasets. For both the datasets (Data190 and Data235), the machine learning approach and the hybrid approach gave good performances in comparison to pattern matching and rule-based approach. Among all the classifiers, AdaBoost outperformed followed by Decision Tree and other classifiers. In the machine learning approach, Decision Tree technique performed better than all the other classifiers using 4-gram feature set by achieving 0.87 F-score, 0.7453 JS and 0.0877 HL. Similarly, in Data235, AdaBoost outperforms by achieving 0.91 F-score, 0.8294 JS and 0.0945 HL.
23
Sohail, Tariq. "Developing market sentiment indicators for commodity price forecasting using machine learning." 2017. http://hdl.handle.net/1993/32038.
Full textAbstract:
The objective of this study is to develop a market sentiment model for financial markets using machine learning, and to illustrate these methods using commodity price data. A market sentiment model may capture the fundamental and crowd psychology of the market, through a variable that uses positive and negative words and phrases. The commodity price used is the daily price of the spot crude oil exchange-traded fund (ETF), United States Oil Fund (USO). The forecasting power of the market sentiment model is compared with a traditional autoregressive model. The results showed that the autoregressive models did not have significant forecasting power for the oil data over the time period examined and the addition of the sentiment model did not improve the forecasting power. Machine learning is a relatively new forecasting method. Therefore, further research on this topic is needed before any firm conclusions can be drawn regarding the effectiveness of this approach.<br>February 2017
24
Marcelino, José Miguel Simões. "SmartSearch – Search Engine with Natural Language Processing." Master's thesis, 2018. http://hdl.handle.net/10316/83559.
Full textAbstract:
Dissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia<br>The world of fashion has recently been receiving a lot of at- tention. At Farfetch, the global platform for luxury, a robust search engine is required to cope with its users’ needs and ex- pectations. The fashion language, with its semantically rich expressions, context and linguistic structure give origin to chal- lenges such as the inability 1) to capture nuances of fashion epithets (for instance, semantically speaking, what is a floral dress?) and, 2) of having an algorithm able to translate the do- main into an effective identification of fashion entities. Natural Language Processing (NLP) endows our systems with capabil- ities to tackle these challenging tasks.Historically, the search engine parser has been keyword-based, involving a large number of constraint rules. This work presents a hierarchical deep learning natural language parser for fash- ion. Our proposal intends not only to recognize fashion-domain entities but also to expose syntactic and morphologic insights. We leverage the usage of an architecture of specialist models, each one for a different task (from parsing to entity recogni- tion). Such architecture renders a hierarchical model able to capture the nuances of the fashion language. The natural lan- guage parser is able to deal with textual ambiguities which are left unresolved by our currently existing solution.We conducted an extensive experimental work to assess the quality of our proposal. Having in mind the complexity of our proposed framework, we conducted an analysis of each module. Achieving 0.98, 0.8 and 0.99 in terms of F1 score in our extrinsic evaluation into the each module (Part-of-Speech (POS), Depen- dency Parsing and Named Entity Recognition (NER) respec- tively) our empirical results establish a robust baseline, which justifies the use of hierarchical architectures of deep learning models while opening new research avenues to explore.<br>O mundo da moda tem vindo a ser alvo de grande destaque. Na Farfetch, a plataforma global de luxo, ́e necess ́ario um mecanismo de pesquisa robusto de modo a cumprir as necessi- dades e expectativas dos utilizadores. A linguagem da moda, com as suas express ̃oes semanticamente ricas, com a sua es- trutura lingu ́ıstica complexa e o seu vago contexto originam grandes desafios, tais como a incapacidade: 1) de captar nu- ances de vocabul ́ario (por exemplo, semanticamente falando, o que ́e um vestido floral?) e, 2) de ter um algoritmo ca- paz de traduzir o dom ́ınio numa identifica ̧c ̃ao efetiva das enti- dades da moda. O Processamento de Linguagem Natural dota os nossos sistemas com capacidades para ultrapassar estas de- safiantes tarefas. Historicamente, o processador do motor de pesquisa tem sido baseado em palavras-chave, envolvendo um vasto nu ́mero de restri ̧c ̃oes. Este trabalho apresenta um pro- cessador de linguagem natural baseado em redes de aprendiza- gem profunda estruturadas de forma hier ́arquica no dom ́ınio da moda. A nossa abordagem pretende n ̃ao s ́o reconhecer as en- tidades do dom ́ınio da moda mas tamb ́em expor conhecimento acerca da sintaxe e morfologia. Baseamo-nos numa arquitetura de modelos especialistas, cada um com um diferente prop ́osito (desde an ́alise sint ́atica a reconhecimento de entidades). Esta arquitetura hier ́arquica permite captar as nuances da moda. O processador de linguagem natural ́e capaz de lidar com am- biguidades que n ̃ao possuem resposta adequada da solu ̧c ̃ao em vigor. Conduzimos uma vasta experimentac ̧ ̃ao de forma a val- idar os nossos resultados. Tendo em conta a complexidade da nossa solu ̧c ̃ao efetuamos uma avalia ̧c ̃ao orientada a cada m ́odulo, tendo obtido valores de ‘F1 score’ de 0.98, 0.8 e 0.99 (respetivamente, An ́alise Sint ́atica, An ́alise de Dependˆencias e Reconhecimento de Entidades). Os nossos resultados emp ́ıricos estabelecem uma base robusta, que justifica o uso de arquite- turas hier ́arquicas de modelos de aprendizagem profunda en- quanto abre novas oportunidades de investiga ̧c ̃ao.