This document explains the use of different metrics involved with record linkage. There are two forms of record linkage: deterministic and probabilistic. We will focus on probabilistic record linkage used in merging and updating two databases. Record pairs will be compared using character-based and phonetic-based similarity metrics to determine at what level they match. Performance measures are then calculated and Receiver Operating Characteristic (ROC) curves are formed. Finally, an economic model is applied that returns the optimal tolerance level two databases should use to determine a record pair match in order to maximize profit.

No description available.

The lack of training data is a common problem in machine learning. One solution to thisproblem is to use transfer learning to remove or reduce the requirement of training data.Selecting datasets for transfer learning can be difficult however. As a possible solution, thisstudy proposes the domain similarity metrics document vector distance (DVD) and termfrequency-inverse document frequency (TF-IDF) distance. DVD and TF-IDF could aid inselecting datasets for good transfer learning when there is no data from the target domain.The simple metric, shared vocabulary, is used as a baseline to check whether DVD or TF-IDF can indicate a better choice for a fine-tuning dataset. SQuAD is a popular questionanswering dataset which has been proven useful for pre-training models for transfer learn-ing. The results were therefore measured by pre-training a model on the SQuAD datasetand fine-tuning on a selection of different datasets. The proposed metrics were used tomeasure the similarity between the datasets to see whether there was a correlation betweentransfer learning effect and similarity. The results found a clear relation between a smalldistance according to the DVD metric and good transfer learning. This could prove usefulfor a target domain without training data, a model could be trained on a big dataset andfine-tuned on a small dataset that is very similar to the target domain. It was also foundthat even small amount of training data from the target domain can be used to fine-tune amodel pre-trained on another domain of data, achieving better performance compared toonly training on data from the target domain.

A medida de similaridade é parte fundamental no corregistro de imagens, guiando todo seu processo. Neste estudo foi feita a comparação entre diferentes métricas de similaridade no contexto do corregistro não rígido (ou elástico) de imagens médicas. Como as imagens cardíacas representam as mais desaadoras situações em corregistro de imagens médicas, foram utilizadas para teste imagens de ressonância magnética nuclear e imagens de ultrasom cardíaco com contraste. 10 métricas de similaridades diferentes foram comparadas extensivamente, quanto ao seu desempenho para o corregistro não rígido: a soma do quadrado das diferenças (SQD), correlação cruzada (CC), correlação cruzada normalizada (CCN), informação mútua (IM), entropia da diferença (ED), variância da diferença (VD), energia (EN), campo de gradiente normalizado (CGN), medida pontual de informação mútua (MPIM), medida pontual de entropia da diferença (MPED). As métricas baseadas em entropias de informação, IM, ED, foram generalizadas em termos da entropia de Tsallis e avaliadas em seu parâmetro q. Os resultados apresentados mostram a eciência das métricas estudadas para diferentes parâmetros, como dimensão da região de comparação entre as imagens, dimensão da região de busca por similaridade, número de tons de cinza das imagens e parâmetro entrópico. Estes achados podem ser úteis para a construção de denições apropriadas para o corregistro não-rígido, utilizado no corregistro de imagens médicas complexas. / The similarity measurement plays a key role in images registration, driving the whole process of registration. In this study a comparison was made between dierent metrics of similarity in the context of non-rigid registration in medical images. As cardiac images represent the most challenging situation in medical image registration, it has been used as test heart magnetic resonance imaging (MRI) and cardiac ultrasound contrast images. In this work ten different similarity metrics have been compared extensively, as well its performance for the non-rigid registration process: the sum of the squared differences (SQD), cross- correlation (CC), normalized cross correlation (CCN), mutual information (IM), the entropy difference (ED), variance of the difference (VD), energy (EN), eld of normalized gradient (CGN), point measure of mutual information (MPIM), point measure of entropy differences (MPED). Metrics based on information entropies, IM, ED were eneralized in terms of Tsallis entropy and evaluated in its parameter q. The presented results show the effectiveness of the studied metrics for different parameters such as similarity window search size, similarity region search size, image maximum gray level, and entropic parameter. These nding can be helpful to construct appropriate non-rigid registration settings for complex medical image registration.

A medida de similaridade é parte fundamental no corregistro de imagens, guiando todo seu processo. Neste estudo foi feita a comparação entre diferentes métricas de similaridade no contexto do corregistro não rígido (ou elástico) de imagens médicas. Como as imagens cardíacas representam as mais desaadoras situações em corregistro de imagens médicas, foram utilizadas para teste imagens de ressonância magnética nuclear e imagens de ultrasom cardíaco com contraste. 10 métricas de similaridades diferentes foram comparadas extensivamente, quanto ao seu desempenho para o corregistro não rígido: a soma do quadrado das diferenças (SQD), correlação cruzada (CC), correlação cruzada normalizada (CCN), informação mútua (IM), entropia da diferença (ED), variância da diferença (VD), energia (EN), campo de gradiente normalizado (CGN), medida pontual de informação mútua (MPIM), medida pontual de entropia da diferença (MPED). As métricas baseadas em entropias de informação, IM, ED, foram generalizadas em termos da entropia de Tsallis e avaliadas em seu parâmetro q. Os resultados apresentados mostram a eciência das métricas estudadas para diferentes parâmetros, como dimensão da região de comparação entre as imagens, dimensão da região de busca por similaridade, número de tons de cinza das imagens e parâmetro entrópico. Estes achados podem ser úteis para a construção de denições apropriadas para o corregistro não-rígido, utilizado no corregistro de imagens médicas complexas. / The similarity measurement plays a key role in images registration, driving the whole process of registration. In this study a comparison was made between dierent metrics of similarity in the context of non-rigid registration in medical images. As cardiac images represent the most challenging situation in medical image registration, it has been used as test heart magnetic resonance imaging (MRI) and cardiac ultrasound contrast images. In this work ten different similarity metrics have been compared extensively, as well its performance for the non-rigid registration process: the sum of the squared differences (SQD), cross- correlation (CC), normalized cross correlation (CCN), mutual information (IM), the entropy difference (ED), variance of the difference (VD), energy (EN), eld of normalized gradient (CGN), point measure of mutual information (MPIM), point measure of entropy differences (MPED). Metrics based on information entropies, IM, ED were eneralized in terms of Tsallis entropy and evaluated in its parameter q. The presented results show the effectiveness of the studied metrics for different parameters such as similarity window search size, similarity region search size, image maximum gray level, and entropic parameter. These nding can be helpful to construct appropriate non-rigid registration settings for complex medical image registration.

There are these methods implemented: circular sectors, color moments, color coherence vector and Gabor filters, they are based on low-level image features. These methods were evaluated after their optimal parameters were found. The finding of optimal parameters of methods is done by measuring of classification accuracy of learning operators and usage of operator cross validation on images in program RapidMiner. Implemented methods are evaluated on these image categories - ancient, beach, bus, dinousaur, elephant, flower, food, horse, mountain and natives, based on total average precision. The classification accuracy result is increased by 8 % by implemented modification (HSB color space + statistical function median) of original method circular sectors. The combination of methods color moments, circular sectors and Gabor filters with weighted ratio gives the best total average precision at 70,48 % and is the best method among all implemented methods.