Global ETD Search

1181	[pt] APLICAÇÃO DE ALGORITMOS DE APRENDIZADO DE MÁQUINA PARA PREVER EFICIÊNCIA ENERGÉTICA BASEADO EM PARÂMETROS DE VIAGEM: ESTUDO DE CASO DE UMA FERROVIA DE TRANSPORTE DE CARGA / [en] APPLICATION OF MACHINE LEARNING ALGORITHMS TO PREDICT FUEL EFFICIENCY BASED ON TRIP PARAMETERS: A HEAVY HAUL RAILWAY CASE OF STUDY RODOLFO SPINELLI TEIXEIRA 21 December 2021 (has links) [pt] O consumo de combustível em empresas do setor de transporte ferroviário representa um dos maiores gastos operacionais e uma das maiores preocupações em termos de emissões de poluentes. O alto consumo em combustíveis acarreta também em uma alta representatividade na matriz de escopo de emissões (mais de 90 por cento das emissões de ferrovias são provenientes do consumo de combustível fóssil). Com o viés de se buscar uma constante melhora operacional, estudos vêm sendo realizados com a finalidade de se propor novas ferramentas na redução do consumo de combustível na operação de um trem de carga. Nesse ramo, destaca-se o aperfeiçoamento dos parâmetros de condução de um trem que são passíveis de calibração com o objetivo de reduzir o consumo de combustível. Para chegar a esse fim, o presente trabalho implementa dois modelos de aprendizado de máquina (machine learning) para prever a eficiência energética de um trem de carga, são eles: floresta randômica e redes neurais artificiais. A floresta randômica obteve o melhor desempenho entre os modelos, apresentando uma acurácia de 91 por cento. Visando calcular quanto cada parâmetro influencia no modelo de previsão, este trabalho também utiliza técnica de efeitos acumulados locais em cada parâmetro em relação à eficiência energética. Os resultados finais mostraram que, dentro dos quatro parâmetros de calibração analisados, o indicador de tração por tonelada transportada apresentou maior representatividade em termos de impacto absoluto na eficiência energética de um trem de carga. / [en] Fuel consumption in companies in the rail transport sector represents one of the largest operating expenses and one of the biggest concerns in terms of pollutant emissions. The high fuel consumption also entails a high representation in the emissions scope matrix (more than 90 percent of railroad emissions come from fossil fuel consumption). Aiming to seek constant operational improvement, numerous studies have been carried out proposing new tools to reduce fuel consumption in the operation of a freight train. In this way, it is important to highlight the improvement of train driving parameters that can be calibrated to reduce fuel consumption. To accomplish this goal, the present work implements two machine learning models to predict the energy efficiency of a freight train: random forest and artificial neural networks. The random forest achieves the best performance against the models, with an accuracy of 91 percent. To calculate how much each parameter influences the prediction model, this work also uses the technique of accumulated local effects for each parameter related to energy efficiency. The final results show that, within the four analyzed calibration parameters, the traction per transported ton indicator presented greater representation in terms of absolute impact on the energy efficiency of a freight train. [pt] APRENDIZADO DE MAQUINA [pt] GRAFICO DE VALORES ACUMULADO LOCAIS [pt] GRAFICO DE DEPENDENCIA PARCIAL [pt] TRANSPORTE PESADO [pt] FLORESTAS ALEATORIAS [pt] EFICIENCIA ENERGETICA [pt] REDES NEURAIS ARTIFICIAIS [pt] CONSUMO ENERGETICO [pt] FERROVIA [en] MACHINE LEARNING [en] ACCUMULATED LOCAL EFFECT PLOT [en] PARTIAL DEPENDENCE PLOT [en] HEAVY HAUL [en] RANDOM FOREST [en] ENERGY EFFICIENCY [en] ARTIFICIAL NEURAL NETWORKS [en] ENERGY CONSUMPTION [en] RAILROAD
1182	Feature Selection for Sentiment Analysis of Swedish News Article Titles / Val av datarepresentation för sentimentsanalys av svenska nyhetsrubriker Dahl, Jonas January 2018 (has links) 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. / 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. sentiment analysis machine learning sentiments ml ai neural networks ann artificial neural networks convolutional neural network cnn language technology natural language news titles Swedish sentimentanalys maskininlärning sentiment ml ai neuronnät ann artificiella neuronnät cnn nyheter nyhetsrubriker språkteknologi Computer Sciences Datavetenskap (datalogi)
1183	Deep Neural Networks for Context Aware Personalized Music Recommendation : A Vector of Curation / Djupa neurala nätverk för kontextberoende personaliserad musikrekommendation Bahceci, Oktay January 2017 (has links) Information Filtering and Recommender Systems have been used and has been implemented in various ways from various entities since the dawn of the Internet, and state-of-the-art approaches rely on Machine Learning and Deep Learning in order to create accurate and personalized recommendations for users in a given context. These models require big amounts of data with a variety of features such as time, location and user data in order to find correlations and patterns that other classical models such as matrix factorization and collaborative filtering cannot. This thesis researches, implements and compares a variety of models with the primary focus of Machine Learning and Deep Learning for the task of music recommendation and do so successfully by representing the task of recommendation as a multi-class extreme classification task with 100 000 distinct labels. By comparing fourteen different experiments, all implemented models successfully learn features such as time, location, user features and previous listening history in order to create context-aware personalized music predictions, and solves the cold start problem by using user demographic information, where the best model being capable of capturing the intended label in its top 100 list of recommended items for more than 1/3 of the unseen data in an offine evaluation, when evaluating on randomly selected examples from the unseen following week. / Informationsfiltrering och rekommendationssystem har använts och implementeratspå flera olika sätt från olika enheter sedan gryningen avInternet, och moderna tillvägagångssätt beror påMaskininlärrning samtDjupinlärningför att kunna skapa precisa och personliga rekommendationerför användare i en given kontext. Dessa modeller kräver data i storamängder med en varians av kännetecken såsom tid, plats och användardataför att kunna hitta korrelationer samt mönster som klassiska modellersåsom matris faktorisering samt samverkande filtrering inte kan. Dettaexamensarbete forskar, implementerar och jämför en mängd av modellermed fokus påMaskininlärning samt Djupinlärning för musikrekommendationoch gör det med succé genom att representera rekommendationsproblemetsom ett extremt multi-klass klassifikationsproblem med 100000 unika klasser att välja utav. Genom att jämföra fjorton olika experiment,så lär alla modeller sig kännetäcken såsomtid, plats, användarkänneteckenoch lyssningshistorik för att kunna skapa kontextberoendepersonaliserade musikprediktioner, och löser kallstartsproblemet genomanvändning av användares demografiska kännetäcken, där den bästa modellenklarar av att fånga målklassen i sin rekommendationslista medlängd 100 för mer än 1/3 av det osedda datat under en offline evaluering,när slumpmässigt valda exempel från den osedda kommande veckanevalueras. Information Filtering Information Retrieval Search Engine Search Engines Recommendation Music Recommendation Personalized Recommendation Personalised Recommendation Context Aware Recommendation Recommender Systems Statistical Learning Artificial Intelligence Machine Learning Deep Learning Neural Networks Artificial Neural Networks Feed Forward Neural Networks Convolutional Neural Networks Recurrent Neural Networks Deep Neural Networks Embedding Computer Sciences Datavetenskap (datalogi)
1184	Classification of Radar Emitters Based on Pulse Repetition Interval using Machine Learning Svensson, André January 2022 (has links) In electronic warfare, one of the key technologies is radar. Radar is used to detect and identify unknown aerial, nautical or land-based objects. An attribute of of a pulsed radar signal is the Pulse Repetition Interval (PRI) which is the time interval between pulses in a pulse train. In a passive radar receiver system, the PRI can be used to recognize the emitter system. Correct classification of emitter systems is a crucial part of Electronic Support Measures (ESM) and Radar Warning Receivers (RWR) in order to deploy appropriate measures depending on the emitter system. Inaccurate predictions of emitter systems can have lethal consequences and variables such as time and confidence in the predictions are essential for an effective predictive method. Due to the classified nature of military systems and techniques, there are no industry standard systems or techniques that perform quick and accurate classifications of emitter systems based on PRI. Therefore, methods that allows for fast and accurate predictions based on PRI is highly desirable and worthy of research. This thesis explores and compares the capabilities of two machine learning methods for the task of classifying emitters based on received PRI. The first method is an attention based model which performs well throughout all levels of realistic noise and is quick to learn and even quicker to give accurate predictions. The second method is a K-Nearest Neighbor (KNN) implementation that, while performing well for noise-free PRI, finds its performance degrading as the amount of noise increases. An additional outcome of this thesis is the development of a system to generate samples in an automated fashion. The attention based model performs well, achieving a macro avarage F1-score of 63% in the 59-class recognition task whereas the performance of the KNN is lower, achieving a macro avarage F1-score of 43%. Future research could be conducted with the purpose of designing a better attention based model for producing higher and more confident predictions and designing algorithms to reduce the time complexity of the KNN implementation. / En av de viktigaste teknikerna inom telektrig är radarn. Radar används för att upptäcka och identifiera okända, luftburna, sjögående eller landbaserade förmål. En komponent av radar är Pulsrepetitionsinterval (Pulse Repetition Intervall, PRI) som beskrivs som tidsintervallet mellan två inkommande pulser. I ett radarvarnar system (Radar Warning Receiver, RWR) kan PRI användas för att identifiera radarsystem. Korrekt identifiering av radarsystem är en viktig uppgift för elektroniska understödsmedel (Electronic Support Measures, ESM) med syfte att tillsätta lämpliga medel beroende på radarsystemet i fråga. Icke tillförlitlig identifiering av radarsystem kan ha dödliga konsekvenser och variabler som tid och säkerhet i identifieringen är avgörande för ett effektivt system. Då dokumentation och specifikationer för militära system i regel är hemligstämplade är det svårt att utröna någon typ av industristandard för att utföra snabb och säker klassificering av radarsystem baserat på PRI. Därför är det av stort intresse detta område och möjligheterna för sådana lösningar utforskas. Detta examensarbete utforskar och jämför förmågorna hos två maskininlärningsmetoder i avseende att korrekt identifiera radarsändare baserat på genererat PRI. Den första metoden är ett djupt neuralt nätverk som använder sig av tekniken ”attention”. Det djupa nätverket presterar bra för alla brusnivåer och lär sig snabbt att känna igen attributen hos PRI som kännetecknar vilken radarsändare och som efter träning dessutom är snabb på att korrekt identifiera PRI. Den andra metoden är en K-Nearest Neighbor implementation som förvisso presterar bra på icke brusig data men vars förmåga försämras allt eftersom brusnivåerna ökar. Ett ytterligare resultat av arbetet är utvecklingen och implementationen av en metod för att specificera PRI och sedan generera PRI efter specifikation. Attention modellen genererar bra prediktioner för data bestående av 59 klasser, med ett F1-score snitt om 63% medan KNN-implementationen för samma uppgift har en lägre träffsäkerhet med ett F1-score snitt om 43%. Vidare forskning kan innefatta utökad utveckling av det djupa, neurala nätverket i syfte att förbättra dess förmåga för identifiering och metoder för att minimera tidsåtgången för KNN implementationen. Radar Warning Systems Pulse Repetition Interval Artificial Neural Networks Attention Transformers K-Nearest Neighbour Classification Data Generation Radar Temporal Sequences Aritficiella Neurala Nätverk Tidsserie data Puls Repetitions Intervall Attention Transformers K-Nearest Neighbor Klassificering Datagenerering Radar Computer and Information Sciences Data- och informationsvetenskap
1185	Deep Reinforcement Learning for Multi-Agent Path Planning in 2D Cost Map Environments : using Unity Machine Learning Agents toolkit Persson, Hannes January 2024 (has links) Multi-agent path planning is applied in a wide range of applications in robotics and autonomous vehicles, including aerial vehicles such as drones and other unmanned aerial vehicles (UAVs), to solve tasks in areas like surveillance, search and rescue, and transportation. In today's rapidly evolving technology in the fields of automation and artificial intelligence, multi-agent path planning is growing increasingly more relevant. The main problems encountered in multi-agent path planning are collision avoidance with other agents, obstacle evasion, and pathfinding from a starting point to an endpoint. In this project, the objectives were to create intelligent agents capable of navigating through two-dimensional eight-agent cost map environments to a static target, while avoiding collisions with other agents and simultaneously minimizing the path cost. The method of reinforcement learning was used by utilizing the development platform Unity and the open-source ML-Agents toolkit that enables the development of intelligent agents with reinforcement learning inside Unity. Perlin Noise was used to generate the cost maps. The reinforcement learning algorithm Proximal Policy Optimization was used to train the agents. The training was structured as a curriculum with two lessons, the first lesson was designed to teach the agents to reach the target, without colliding with other agents or moving out of bounds. The second lesson was designed to teach the agents to minimize the path cost. The project successfully achieved its objectives, which could be determined from visual inspection and by comparing the final model with a baseline model. The baseline model was trained only to reach the target while avoiding collisions, without minimizing the path cost. A comparison of the models showed that the final model outperformed the baseline model, reaching an average of $27.6\%$ lower path cost. / Multi-agent-vägsökning används inom en rad olika tillämpningar inom robotik och autonoma fordon, inklusive flygfarkoster såsom drönare och andra obemannade flygfarkoster (UAV), för att lösa uppgifter inom områden som övervakning, sök- och räddningsinsatser samt transport. I dagens snabbt utvecklande teknik inom automation och artificiell intelligens blir multi-agent-vägsökning allt mer relevant. De huvudsakliga problemen som stöts på inom multi-agent-vägsökning är kollisioner med andra agenter, undvikande av hinder och vägsökning från en startpunkt till en slutpunkt. I detta projekt var målen att skapa intelligenta agenter som kan navigera genom tvådimensionella åtta-agents kostnadskartmiljöer till ett statiskt mål, samtidigt som de undviker kollisioner med andra agenter och minimerar vägkostnaden. Metoden förstärkningsinlärning användes genom att utnyttja utvecklingsplattformen Unity och Unitys open-source ML-Agents toolkit, som möjliggör utveckling av intelligenta agenter med förstärkningsinlärning inuti Unity. Perlin Brus användes för att generera kostnadskartorna. Förstärkningsinlärningsalgoritmen Proximal Policy Optimization användes för att träna agenterna. Träningen strukturerades som en läroplan med två lektioner, den första lektionen var utformad för att lära agenterna att nå målet, utan att kollidera med andra agenter eller röra sig utanför gränserna. Den andra lektionen var utformad för att lära agenterna att minimera vägkostnaden. Projektet uppnådde framgångsrikt sina mål, vilket kunde fastställas genom visuell inspektion och genom att jämföra den slutliga modellen med en basmodell. Basmodellen tränades endast för att nå målet och undvika kollisioner, utan att minimera vägen kostnaden. En jämförelse av modellerna visade att den slutliga modellen överträffade baslinjemodellen, och uppnådde en genomsnittlig $27,6\%$ lägre vägkostnad. deep reinforcement learning reinforcement learning machine learning path planning cost map ML-agents unity artificial neural networks collision avoidance PPO multi agent multi-agent multi-agent system förstärkningsinlärning djup förstärkningsinlärning fleragentssystem kostnadkarta kostnadskartor artificiella neurala nätverk maskininlärning proximal policy optimization PPO svärmintelligens
1186	Eco-climatic assessment of the potential establishment of exotic insects in New Zealand Peacock, Lora January 2005 (has links) To refine our knowledge and to adequately test hypotheses concerning theoretical and applied aspects of invasion biology, successful and unsuccessful invaders should be compared. This study investigated insect establishment patterns by comparing the climatic preferences and biological attributes of two groups of polyphagous insect species that are constantly intercepted at New Zealand's border. One group of species is established in New Zealand (n = 15), the other group comprised species that are not established (n = 21). In the present study the two groups were considered to represent successful and unsuccessful invaders. To provide background for interpretation of results of the comparative analysis, global areas that are climatically analogous to sites in New Zealand were identified by an eco-climatic assessment model, CLIMEX, to determine possible sources of insect pest invasion. It was found that south east Australia is one of the regions that are climatically very similar to New Zealand. Furthermore, New Zealand shares 90% of its insect pest species with that region. South east Australia has close trade and tourism links with New Zealand and because of its proximity a new incursion in that analogous climate should alert biosecurity authorities in New Zealand. Other regions in western Europe and the east coast of the United States are also climatically similar and share a high proportion of pest species with New Zealand. Principal component analysis was used to investigate patterns in insect global distributions of the two groups of species in relation to climate. Climate variables were reduced to temperature and moisture based principal components defining four climate regions, that were identified in the present study as, warm/dry, warm/wet, cool/dry and cool/moist. Most of the insect species established in New Zealand had a wide distribution in all four climate regions defined by the principal components and their global distributions overlapped into the cool/moist, temperate climate where all the New Zealand sites belong. The insect species that have not established in New Zealand had narrow distributions within the warm/wet, tropical climates. Discriminant analysis was then used to identify which climate variables best discriminate between species presence/absence at a site in relation to climate. The discriminant analysis classified the presence and absence of most insect species significantly better than chance. Late spring and early summer temperatures correctly classified a high proportion of sites where many insect species were present. Soil moisture and winter rainfall were less effective discriminating the presence of the insect species studied here. Biological attributes were compared between the two groups of species. It was found that the species established in New Zealand had a significantly wider host plant range than species that have not established. The lower developmental threshold temperature was on average, 4°C lower for established species compared with non-established species. These data suggest that species that establish well in New Zealand have a wide host range and can tolerate lower temperatures compared with those that have not established. No firm conclusions could be drawn about the importance of propagule pressure, body size, fecundity or phylogeny for successful establishment because data availability constrained sample sizes and the data were highly variable. The predictive capacity of a new tool that has potential for eco-climatic assessment, the artificial neural network (ANN), was compared with other well used models. Using climate variables as predictors, artificial neural network predictions were compared with binary logistic regression and CLIMEX. Using bootstrapping, artificial neural networks predicted insect presence and absence significantly better than the binary logistic regression model. When model prediction success was assessed by the kappa statistic there were also significant differences in prediction performance between the two groups of study insects. For established species, the models were able to provide predictions that were in moderate agreement with the observed data. For non-established species, model predictions were on average only slightly better than chance. The predictions of CLIMEX and artificial neural networks when given novel data, were difficult to compare because both models have different theoretical bases and different climate databases. However, it is clear that both models have potential to give insights into invasive species distributions. Finally the results of the studies in this thesis were drawn together to provide a framework for a prototype pest risk assessment decision support system. Future research is needed to refine the analyses and models that are the components of this system. analogous climates artificial neural networks CLIMEX discriminate analysis establishment success host plant invasive species kappa statistic pest risk analysis polyphagous insect pest species principal component analysis eco-climatic assessment model
1187	基於 EEMD 與類神經網路方法進行台指期貨高頻交易研究 / A Study of TAIEX Futures High-frequency Trading by using EEMD-based Neural Network Learning Paradigms 黃仕豪, Huang, Sven Shih Hao Unknown Date (has links) 金融市場是個變化莫測的環境，看似隨機，在隨機中卻隱藏著某些特性與關係。不論是自然現象中的氣象預測或是金融領域中對下一時刻價格的預測, 都有相似的複雜性。時間序列的預測一直都是許多領域中重要的項目之一, 金融時間序列的預測也不例外。在本論文中我們針對金融時間序列的非線性與非穩態關係引入類神經網路(ANNs) 與集合經驗模態分解法(EEMD), 藉由ANNs處理非線性問題的能力與EEMD處理時間序列信號的優點，並進一步與傳統上使用於金融時間序列分析的自回歸滑動平均模型(ARMA)進行複合式的模型建構，引入燭型圖概念嘗試進行高頻下的台指期貨TAIEX交易。在不計交易成本的績效測試下本研究的高頻交易模型有突出的績效，證明以ANNs、EEMD方法與ARMA組成的混合式模型在高頻時間尺度交易下有相當的發展潛力，具有進一步發展的價值。在處理高頻時間尺度下所產生的大型數據方面，引入平行運算架構SPMD(single program, multiple data)以增進其處理大型資料下的運算效率。本研究亦透過分析高頻時間尺度的本質模態函數(IMFs)探討在高頻尺度下影響台指期貨價格的因素。 / Financial market is complex, unstable and non-linear system, it looks like have some principle but the principle usually have exception. The forecasting of time series always an issue in several field include finance. In this thesis we propose several version of hybrid models, they combine Ensemble Empirical Mode Decomposition (EEMD), Back-Propagation Neural Networks(BPNN) and ARMA model, try to improve the forecast performance of financial time series forecast. We also found the physical means or impact factors of IMFs under high-frequency time-scale. For processing the massive data generated by high-frequency time-scale, we pull in the concept of big data processing, adopt parallel computing method ”single program, multiple data (SPMD)” to construct the model improve the computing performance. As the result of backtesting, we prove the enhanced hybrid models we proposed outperform the standard EEMD-BPNN model and obtain a good performance. It shows adopt ANN, EEMD and ARMA in the hybrid model configure for high-frequency trading modeling is effective and it have the potential of development. 類神經網路方法燭型圖(K線圖) 自回歸滑動平均模型集合經驗模態分解法高頻交易平行運算時間序列分析大型數據處理 Artificial Neural Networks Candlestick Charts Autoregressive Moving Average model Ensemble Empirical Mode Decomposition High-Frequency Trading Parallel Computing Time series analysis Big Data Processing
1188	Medical image captioning based on Deep Architectures / Medicinsk bild textning baserad på Djupa arkitekturer Moschovis, Georgios January 2022 (has links) Diagnostic Captioning is described as “the automatic generation of a diagnostic text from a set of medical images of a patient collected during an examination” [59] and it can assist inexperienced doctors and radiologists to reduce clinical errors or help experienced professionals increase their productivity. In this context, tools that would help medical doctors produce higher quality reports in less time could be of high interest for medical imaging departments, as well as significantly impact deep learning research within the biomedical domain, which makes it particularly interesting for people involved in industry and researchers all along. In this work, we attempted to develop Diagnostic Captioning systems, based on novel Deep Learning approaches, to investigate to what extent Neural Networks are capable of performing medical image tagging, as well as automatically generating a diagnostic text from a set of medical images. Towards this objective, the first step is concept detection, which boils down to predicting the relevant tags for X-RAY images, whereas the ultimate goal is caption generation. To this end, we further participated in ImageCLEFmedical 2022 evaluation campaign, addressing both the concept detection and the caption prediction tasks by developing baselines based on Deep Neural Networks; including image encoders, classifiers and text generators; in order to get a quantitative measure of my proposed architectures’ performance [28]. My contribution to the evaluation campaign, as part of this work and on behalf of NeuralDynamicsLab¹ group at KTH Royal Institute of Technology, within the school of Electrical Engineering and Computer Science, ranked 4th in the former and 5th in the latter task [55, 68] among 12 groups included within the top-10 best performing submissions in both tasks. / Diagnostisk textning avser automatisk generering från en diagnostisk text från en uppsättning medicinska bilder av en patient som samlats in under en undersökning och den kan hjälpa oerfarna läkare och radiologer, minska kliniska fel eller hjälpa erfarna yrkesmän att producera diagnostiska rapporter snabbare [59]. Därför kan verktyg som skulle hjälpa läkare och radiologer att producera rapporter av högre kvalitet på kortare tid vara av stort intresse för medicinska bildbehandlingsavdelningar, såväl som leda till inverkan på forskning om djupinlärning, vilket gör den domänen särskilt intressant för personer som är involverade i den biomedicinska industrin och djupinlärningsforskare. I detta arbete var mitt huvudmål att utveckla system för diagnostisk textning, med hjälp av nya tillvägagångssätt som används inom djupinlärning, för att undersöka i vilken utsträckning automatisk generering av en diagnostisk text från en uppsättning medi-cinska bilder är möjlig. Mot detta mål är det första steget konceptdetektering som går ut på att förutsäga relevanta taggar för röntgenbilder, medan slutmålet är bildtextgenerering. Jag deltog i ImageCLEF Medical 2022-utvärderingskampanjen, där jag deltog med att ta itu med både konceptdetektering och bildtextförutsägelse för att få ett kvantitativt mått på prestandan för mina föreslagna arkitekturer [28]. Mitt bidrag, där jag representerade forskargruppen NeuralDynamicsLab² , där jag arbetade som ledande forskningsingenjör, placerade sig på 4:e plats i den förra och 5:e i den senare uppgiften [55, 68] bland 12 grupper som ingår bland de 10 bästa bidragen i båda uppgifterna. Artificial Neural Networks Deep Learning Speech and language technology Natural Language Processing (NLP) Deep networks Generative deep networks Convolutional neural networks (CNN) Text generation Information retrieval Diagnostic captioning Image captioning concept prediction classification image encoders transformers Encoder-Decoder architecture abstractive summarization Neurala nätverk Djup inlärning Tal-och språkteknologi naturlig språkbehandling djup neurala nätverk generativa djupa nätverk konvolutionella neurala nätverk Textgenerering Informationssökning Diagnostisk textning Bildtextning konceptförutsägelse klassificering bildkodare transformatorer kodaravkodararkitektur abstrakt sammanfattning Computer and Information Sciences Data- och informationsvetenskap
1189	Forecasting Models to Predict EQ-5D Model Indicators for Population Health Improvement Pathak, Amit January 2016 (has links) No description available. Aging Artificial Intelligence Behavioral Psychology Behavioral Sciences Behaviorial Sciences Cognitive Psychology Demography Demographics Developmental Psychology Economics Educational Tests and Measurements Evolution and Development Finance Gender Studies Health Health Care Health Care Management Health Sciences Higher Education Industrial Engineering Information Science Information Systems Information Technology Literacy Mental Health Public Health Public Policy Sanitation Social Psychology Social Research Statistics Sustainability Population Health EQ-5D Forecasting Policy Artificial Neural Networks Statistics Healthcare Visualize Data Decision World Bank,World Health Organization WHO United Nations Development Programme UNDP Indicator Regression Exploratory Principal Components
1190	Revision of an artificial neural network enabling industrial sorting Malmgren, Henrik January 2019 (has links) Convolutional artificial neural networks can be applied for image-based object classification to inform automated actions, such as handling of objects on a production line. The present thesis describes theoretical background for creating a classifier and explores the effects of introducing a set of relatively recent techniques to an existing ensemble of classifiers in use for an industrial sorting system.The findings indicate that it's important to use spatial variety dropout regularization for high resolution image inputs, and use an optimizer configuration with good convergence properties. The findings also demonstrate examples of ensemble classifiers being effectively consolidated into unified models using the distillation technique. An analogue arrangement with optimization against multiple output targets, incorporating additional information, showed accuracy gains comparable to ensembling. For use of the classifier on test data with statistics different than those of the dataset, results indicate that augmentation of the input data during classifier creation helps performance, but would, in the current case, likely need to be guided by information about the distribution shift to have sufficiently positive impact to enable a practical application. I suggest, for future development, updated architectures, automated hyperparameter search and leveraging the bountiful unlabeled data potentially available from production lines. artificial neural networks machine learning deep learning connectionism pattern recognition machine learning automation image analysis information technology applied mathematics mathematical optimization information theory mathematical statistics mathematical models stochastic models probabilities chance approximations algorithms computer programs computer software signal processing high performance computing numerical methods high technology industries sustainable development artificiella neurala nätverk maskininlärning djup maskininlärning konnektionism mönsterigenkänning automatisering bildanalys informationsteknik tillämpad matematik optimering informationsteori statistisk inferens matematiska modeller stokastiska modeller sannolikhetskalkyl slumpen approximationer algoritmer datorprogram programvara signalbehandling högpresterande beräkningar numeriska metoder teknikutveckling maskinindustri högteknologisk industri maskinhandel skrothandel bärkraftig utveckling Robotics Robotteknik och automation Probability Theory and Statistics Sannolikhetsteori och statistik Other Computer and Information Science Annan data- och informationsvetenskap Signal Processing Signalbehandling

Search results