Background: Age estimation has attracted attention because of its various clinical and medical applications. There are many studies on human age estimation from biomedical images such as X-ray images, MRI, facial images, dental images etc. However, there is no research done on mammograms for age estimation. Therefore, in our research, we focus on age estimation from mammogram images. Objectives: The purpose of this study is to make an AI-based model for estimating age from mammogram images based on the pectoral muscle segment and check its accuracy. At first, we segment the pectoral muscle from mammograms. Then we extract deep learning features and handcrafted features from the pectoral muscle segment as well as other regions for comparison. From these features, we built models to estimate the age. Methods: We have selected an experiment method to answer our research question. We have used the U-net model for pectoral muscle segmentation. After that, we have extracted handcrafted features and deep learning features from pectoral muscle using ResNet-50 and Xception. Then we trained Support Vector Regression and Random Forest models to estimate the age based on the pectoral muscle of mammograms. Finally, we observed how accurately these models are in estimating the age by comparing the MSE and MAE values. We have considered breast region (BR) and the whole MLO to answer our research question. Results: The MAE values for both SVR and RF models from handcrafted features is around 10 in years in all cases. On the other hand, with deep learning features MAE is less as compared to handcrafted features. In our experiment, the least observed error value for MAE was around 8.4656 years for the model that extracted the features from the whole MLO using ResNet50 and SVR as the regression model. Conclusions: We have concluded that the breast region (BR) is more accurate in estimating the age compared to PM by having least MAE and MSE values in its models. Moreover, we were able to observe that handcrafted feature models are not as accurate as deep feature models in estimating the age from mammograms.

Machine Learning (ML) is a research area in artificial intelligence (AI) and computer science. ML focuses on the use of data and algorithms to identify patterns in data without direct instruction. This is done with the help of ML algorithms that learn to make predictions by finding rules and drawing conclusions based on training data. ML can be used to perform tasks such as estimating human's age based on facial images, which can be used to control or restrict access to a website based on the user's age.Age estimation from facial images can be described as a regression problem or a classification problem. Estimating the exact age is a regression problem, while estimating the age group is a classification problem. A regression problem can be converted to a classification problem to determine the age group from the estimated age. This is done by dividing the total age range into different age groups, after which it is decided which group the age estimate belongs to. This study aims to answer how ML models can be used to estimate different age groups from facial images. This is done by exploring and evaluating two classification models that directly estimate the age group, in comparison with determining the age group from the exact age estimate by converting the regression problem into a classification problem. In this work, facial images are used to train and test ML algorithms by combining facial images from various open research databases. A delimitation was made in this study to only explore the use of Convolutional Neural Networks (CNN) to create different ML models that can estimate the age or the age group. CNN are used to perform tasks that require image interpretation, which in this case means that facial images are interpreted to make predictions. The results show that one of two classification models in this study achieves an accuracy of 75.9%. The second classification model, which estimates other age groups, achieves an accuracy of 62.88%. However, the outcome of two converted classification problems from a regression model shows an accuracy of 68.85% and 70.68%, respectively. The estimation model that achieves the highest accuracy when estimating the age group is a classification model with 75.90% accuracy. The work indicates that the choice of age group interval and facial images within each age group determine how the estimation models perform in relation to each other. / Machine Learning (ML) är ett forskningsområde inom artificiell intelligens (AI) och datavetenskap. ML fokuserar på användningen av data och algoritmer för att identifiera mönster i data utan direkt instruktion. Detta sker med hjälp av ML-algoritmer som lär sig att göra förutsägelser genom att hitta regler och dra slutsatser utifrån träningsdata. ML kan användas för att utföra uppgifter som att uppskatta människors ålder utifrån ansiktsbilder, vilket kan användas för att kontrollera eller begränsa åtkomsten till en webbplats baserat på användarens ålder. Åldersuppskattning från ansiktsbilder kan beskrivas som ett regressionsproblem eller ett klassificeringsproblem. Att uppskatta den exakta åldern är ett regressionsproblem, medan att uppskatta åldersgruppen är ett klassificeringsproblem. Ett regressionsproblem kan konverteras till ett klassificeringsproblem för att bestämma åldersgruppen från den uppskattade åldern. Detta utförs genom att dela upp det totala åldersintervallet i olika åldersgrupper, varefter det avgörs vilken grupp åldersuppskattningen tillhör. Denna studie ämnar svara på hur ML-modeller kan användas för att uppskatta olika åldersgrupper från ansiktsbilder. Detta sker genom att utforska och utvärdera två klassificeringsmodeller som direkt uppskattar åldersgruppen, i jämförelse med att bestämma åldersgruppen från den exakta åldersuppskattningen genom att konvertera regressionsproblemet till ett klassificeringsproblem. I detta arbete används ansiktsbilder för att träna och testa ML-algoritmer genom att kombinera ansiktsbilder från olika öppna forskningsdatabaser. En avgränsning gjordes i denna studie för att endast undersöka användningen av Convolutional Neural Networks (CNN) för att skapa olika ML-modeller som kan uppskatta åldern eller åldersgruppen. CNN används för att utföra uppgifter som kräver bildtolkning, vilket i det här fallet innebär att ansiktsbilder tolkas för att göra förutsägelser. Resultaten visar att en av två klassificeringsmodeller i denna studie uppnår en noggrannhet på 75,9%. Den andra klassificeringsmodellen, som uppskattar andra åldersgrupper, uppnår en noggrannhet på 62,88%. Däremot visar utfallet av två konverterade klassificeringsproblem från en regressionsmodell en noggrannhet på 68,85% respektive 70,68%. Den uppskattningsmodell som uppnår högsta noggrannhet vid uppskattning av åldersgruppen är en klassificeringsmodell med 75,90% noggrannhet. Arbetet tyder på att valet av åldergruppintervallet samt ansiktsbilder inom varje åldersgrupp avgör hur uppskattningsmodellerna presterar i förhållande till varandra.

No description available.

Yes / Automatic facial age progression (AFAP) has been an active area of research in recent years. This is due to its numerous applications which include searching for missing. This study presents a new method of AFAP. Here, we use an Active Appearance Model (AAM) to extract facial features from available images. An ageing function is then modelled using Sparse Partial Least Squares Regression (sPLS). Thereafter, the ageing function is used to render new faces at different ages. To test the accuracy of our algorithm, extensive evaluation is conducted using a database of 500 face images with known ages. Furthermore, the algorithm is used to progress Ben Needham’s facial image that was taken when he was 21 months old to the ages of 6, 14 and 22 years. The algorithm presented in this paper could potentially be used to enhance the search for missing people worldwide.

Identification of human or nonhuman skeletal remains is important in assisting the police and law enforcement officers for the investigation of forensic cases. Identification of bone can be difficult, especially in fragmented remains. It has been reported that 25 to 30% of medicolegal cases, which involved nonhuman skeletal remains have been mistaken for human. In such cases, histomorphometric method was used to identify human and nonhuman skeletal remains. However, literature has shown that histomorphometric data for human and nonhuman bone were insufficient. Additionally, age estimation in bone may help in the identification of human individual, which can be done by using a histomorphometric method. Age estimation is based on bone remodeling process, where microstructural parameters have strong correlations with age. Literature showed that age estimation has been done on the American and European populations. However, little work has been done in the Asian population. The aims of this project were thus, to identify human and nonhuman bone, and to estimate age in human bones by using histomorphometric analysis. In this project, 64 human bones and 65 animal bones were collected from the mortuary of the Universiti Kebangsaan Malaysia Medical Centre and the Zoos in Malaysia, respectively. A standard bone preparation was used to prepare human and nonhuman bone thin sections for histomorphometric assessment. Assessments were made on the microstructural parameters such as cortical thickness, medullary cavity diameter, osteon count, osteon diameter, osteon area, osteon perimeter, Haversian canal diameter, Haversian canal area, Haversian canal perimeter, and Haversian lamella count per osteon by using image analysis, and viewed under a transmitted light microscope. The microstructural measurements showed significant differences between human and nonhuman samples. The discriminant functions showed correct classification rates for 81.4% of cases, and the accuracy of identification was 96.9% for human and 66.2% for animal. Human age estimation showed a standard error of estimate of 10.41 years, comparable with those in the literature. This study project offers distinct advantages over currently available histomorphometric methods for human and nonhuman identification and human age estimation. This will have significant implications in the assessment of fragmentary skeletal and forensic population samples for identification purposes.

Este trabalho apresenta uma proposta de metodologia de estimação de idade óssea baseada em características métricas, utilizando o banco de imagens carpais da Escola de Engenharia de São Carlos (EESC). As imagens foram devidamente segmentadas para obtenção da área, perímetro e comprimento de cada osso, gerando, assim, um banco de dados métricos o CarpEven. As informações da base métrica CarpEven foram submetidas a dois mineradores de dados: ao StARMiner, (Statistical Association Rules) uma metodologia de mineração de dados criada por um grupo de pesquisadores do ICMC-USP, e ao Weka (Waikato Environment for Knowledge Analysis), desenvolvido pela Universidade Waikato da Nova Zelândia. As informações foram submetidas a classificadores neurais, contribuindo, assim, para a criação de uma nova metodologia de estimação de idade óssea. Finalmente, é feita uma comparação entre os resultados obtidos e os resultados já alcançados por outras pesquisas. / This work presents a methodology for bone age estimation based on metric characteristics using the carpal images database from Engineering School of São Carlos (EESC-USP). The images were properly segmented to obtain the area, perimeter and length of each bone, thus generating a metric database named CarpEven. The database information were submitted to two data miners: the StarMiner (Statistical Association Rules Miner) a methodology for data mining created by a group of researchers from ICMC-USP, and the Weka (Waikato Environment for Knowledge Analysis), developed by the University of Waikato in New Zealand. The information was submitted to the neural classifiers contributing to the creation of a new methodology for bone age estimation. The results are compared with those obtained by others research.

O estudo minucioso das características físicas e químicas dos artefatos cerâmicos, associado com as pesquisas históricas e arqueológicas tem pennitido a reconstituição dos costumes culturais e modos de vida das comunidades antigas. O presente estudo objetivou estudar composição química elementar e mineralógica de cerâmicas arqueológicas coletadas nos sítios .lustino, São José, Curítuba, Saco da Onça, Porto Belo e Vitória Régia, localizados na região do Baixo São Francisco, Sergipe, Brasil. Por meio da análise por ativação com nêutrons instrumental (AANl) e difratometria de raios - X (DRX), pennitiuse definir grupos composicionais de cerâmicas conforme a similaridade química da pastas cerâmica, a qual reflete a composição da matéria-prima utilizada em sua manufatura pelo homem pré-histórico, e inferir a atmosfera e temperatura de queima da cerâmica. As amostras abeiTantes foram identificadas por meio das distâncias Mahalanobis clássica e robusta. O efeito do tempero na pasta cerâmica foi estudado por meio do filtro de Mahalanobis modificado. Os resultados foram interpretados por meio da análise de agioipamento, análise das componentes principais e análise discriminante. O horizonte temporal das cerâmicas foi verificado por meio de técnicas de datação tennoluminescência (TL). Os resultados obtidos neste trabalho, em associação com infonnações oriundas da Arqueologia, pennitiram a identificação dos gi-upos cerâmicos correspondentes às ocupações ceramistas no sítio Justino e a definição de gi\'upos cerâmicos de referência confonne o comportamento químico. A tecnologia de queima foi estabelecida para alguns vasos cerâmicos, bem como a contemporaneidade dos grupos composicionais segundo as datações determinadas por TL. Dessa forma, o trabalho contribui para a reconstituição da pré-história das comunidades que habitaram a região do Baixo Rio São Francisco e para remontagem do quadro geral das populações ceramistas do Nordeste brasileiro. / The study of the physical and chemical characteristics of the ceramics crafts, in association with historical and archaeological research, has allowed for the reconstruction of the cultural habits from ancient communities. The goal of this work was to study the chemical and mineralogical compositions of archaeological potteries collected from Justino, São José, Curituba, Saco da Onça, Porto Belo and Vitória Régia sites, located in Baixo São Francisco region, Sergipe state, Brazil. The use of the instrumental neutron activation analysis (INAA) and X-ray diffractometry (XRD), allowed the definition of compositional groups of potteries according to the chemical similarities of the ceramic paste, which reveals the composition of the raw materials utilized in the manufacturing process by prehistoric man, and the inference of the atmosphere and temperatures in which the potteries were burned. The outliers were identified by means of classic and robust Mahalanobis distance. The temper effect in the ceramic paste was studied by means of modified Mahalanobis filter. The results were interpreted by means of cluster analysis, principal components analysis and discriminant analysis. The ages of some potteries were determined by means of the thermoluminescence techniques. The results obtained in this work, in association with archaeological information, allowed for the identification of the ceramic groups relative to ceramist occupations at Justino Site and for the definition of the reference groups according to the chemical composition. The burning technology was established for some potteries and the relative ages among the compositional groups were determined by means of TL. Thus, this work provides contributions to the reconstmction of the prehistory of the communities which lived in the Baixo São Francisco region, and to the reconstitution of the general frame of the ceramist population from Brazilian Northeast.

Nenhuma / Diversos trabalhos na literatura têm utilizado análises de U-Th-Pb obtidas por microssonda eletrônica para a datação química de episódios de fechamento do sistema U-Th-Pb em minerais. Tais episódios podem ser de natureza metamórfica, termal, intempérica ou ainda estar ligados a processos de fissão natural. Diferentes minerais de urânio e/ou tório contendo chumbo radiogênico têm sido analisados com esse propósito. Na região de Lagoa Real (BA) situa-se a única mina de urânio em atividade na América Latina, controlada pela INB (Indústrias Nucleares do Brasil). Os albititos, rochas portadoras de urânio exploradas nessa mina, guardam diversos minerais portadores de urânio e/ou tório tais como uraninita, titanita, zircão, epidoto, allanita-Ce, uranofana e autunita. Ao longo do tempo, diferentes episódios geológicos afetaram heterogeneamente esses minerais. Nesta dissertação foram investigados titanita e zircão com teores variáveis de urânio e chumbo, através da datação química U-Th-Pb em microssonda eletrônica. Os dados obtidos para a titanita indicaram várias idades: 2052 80 Ma, idade aparente interpretada como a idade da cristalização magmática, bem como 1701 57 Ma, 1488 64 Ma, 1298 69 Ma, 1108 78 Ma e 978 58 Ma, idades aparentes interpretadas como resposta aos eventos hidrotermais sofridos pelo mineral. Os dados obtidos para o zircão não foram conclusivos. Além desses minerais, foram datadas uranofanas ricas em ferro e chumbo radiogênico que revelaram também cinco idades aparentes diferentes, muito próximas às mencionadas para a titanita. Essas uranofanas confirmam as múltiplas mobilizações de urânio e chumbo ao longo do Proterozóico, ocorridas durante os referidos eventos hidrotermais. Datações em allanita-Ce mostraram cinco idades aparentes. Por essas idades estarem acima da idade da Terra, elas permitem sugerir que o Pb mobilizado durante os eventos hidrotermais (em número de cinco, indicados pela titanita) estaria sendo sucessivamente incorporado na allanita-Ce e que esse mineral já existiria, pelo menos em parte, concomitantemente com a titanita. Os dados obtidos em epidoto mostraram uma única idade aparente, também acima da idade da Terra, que parece indicar incorporação de chumbo em um único evento, provavelmente o Brasiliano, apontando para sua formação mais tardia na rocha. Essa idade anômala, apesar de não indicar um momento geológico real, aponta para um episódio de incorporação de chumbo pelo epidoto. As uraninitas, principalmente aquelas associadas ao epidoto, apontaram uma idade aparente de 489,3 7,0 Ma, indicativa da influência do evento Brasiliano na região de Lagoa Real. O panorama geocronológico apresentado questiona modelos metassomáticos precedentes para os albititos de Lagoa Real e a mineralização de urânio. Juntamente com recentes dados U-Pb por LA-ICP-MS da literatura, as idades aparentes dos minerais dos albititos sugerem a cristalização do protólito, um sienito sódico uranífero, há aproximadamente 2,0 Ga. Subseqüente metamorfismo há 1,9 Ga parece ter ocorrido durante os estados finais da orogênese orosiriana, quando uma primeira geração de uraninitas foi formada. Múltiplas mobilizações de urânio e chumbo promovidas por cinco eventos hidrotermais (em torno 1,7 Ga, 1,5 Ga, 1,3 Ga, 1,1 Ga e 1,0 Ga) foram detectadas em tais rochas. Como já dito, uma provável geração de um segundo grupo de uraninitas e/ou reinício da contagem do tempo pelo relógio U-Pb de uraninitas mais antigas durante um segundo evento orogênico, por volta de 0,5 Ga (Brasiliano), também ocorreram. A uranofana e a autunita apresentaram idades aparentes de 26,7 Ma e 10,9 Ma, respectivamente, indicativas do intemperismo recente. / Different works in literature have used U-Th-Pb electron microprobe analyses for the chemical dating of U-Th-Pb system closing episodes in minerals. These episodes could have either metamorphic, thermal, and weathering nature or could be related to natural fission processes. Different thorium and uranium-bearing minerals which contain radiogenic lead have been analyzed for this purpose. At the region of Lagoa Real (BA) is located the only active uranium mine in Latin America, controlled by INB (Nuclear Industries of Brazil). The albitites, uraniferous rocks explored in this mine, preserve a lot of thorium and/or uraniumbearing minerals like uraninite, titanite, zircon, epidote, allanite-Ce, uranophane, and autunite. Different geologic episodes should have affected these minerals along time. At this dissertation, zircon and titanite with different uranium and lead contents have been examined by U-Th-Pb electron microprobe dating. The data acquired for zircon had not been conclusive. The data obtained for titanite indicated some ages: 2052 80 Ma, interpreted as the magmatic crystallization apparent age as well as 1701 57 Ma, 1488 64 Ma, 1298 69 Ma, 1108 78 Ma and the 978 58 Ma, interpreted as response to hydrothermal events. In addition to these minerals, Fe and Pb rich uranophanes had been dated, which shown five different ages, close to the ones mentioned for titanite. These uranophanes are the record of multiple lead and uranium mobilizations during Proterozoic, which took place throughout hydrothermal events. Allanite-Ce presented five ages which are older than earths age. They suggest that the Pb mobilized during the hydrothermal events (in number of five, indicated by the titanite) was successively incorporated in the allanite-Ce structure and that this mineral already would exist, at least in part, concomitantly with titanite. The epidote data had shown only one very old anomalous age, which may indicate lead incorporation in only one event, probably the Brasiliano. Uraninites, mainly those related to epidotes, indicated na apparent age of 489.3 7.0 Ma, which shows the Brasiliano event action over Lagoa Real region. The geochronological scenario presented questions previous metasomatic models for Lagoa Real albitites and uranium mineralization. Along with recent LA-ICP-MS U-Pb data from literature, the apparent mineral ages suggest an uraniferous sodic syenitic protolith cristallization 2.0 Ga ago. A 1.9 Ga subsequent metamorphism took place during final moments of the orosirian orogenesis, when a first uraninite group was generated. Uranium and lead multiple mobilizations yielded by five hydrothermal events (ca 1.7 Ga, 1.5 Ga, 1.3 Ga, 1.1 Ga, and 1.0 Ga) were detected in albitites. As metioned, another uraninite group and/or reset of older uraninite U-Pb system during Brasiliano event also took place. Ordinary uranophane and autunite had presented 26,7 Ma and 10,9 Ma ages respectively, indicative of recent weathering.

O estudo minucioso das características físicas e químicas dos artefatos cerâmicos, associado com as pesquisas históricas e arqueológicas tem pennitido a reconstituição dos costumes culturais e modos de vida das comunidades antigas. O presente estudo objetivou estudar composição química elementar e mineralógica de cerâmicas arqueológicas coletadas nos sítios .lustino, São José, Curítuba, Saco da Onça, Porto Belo e Vitória Régia, localizados na região do Baixo São Francisco, Sergipe, Brasil. Por meio da análise por ativação com nêutrons instrumental (AANl) e difratometria de raios - X (DRX), pennitiuse definir grupos composicionais de cerâmicas conforme a similaridade química da pastas cerâmica, a qual reflete a composição da matéria-prima utilizada em sua manufatura pelo homem pré-histórico, e inferir a atmosfera e temperatura de queima da cerâmica. As amostras abeiTantes foram identificadas por meio das distâncias Mahalanobis clássica e robusta. O efeito do tempero na pasta cerâmica foi estudado por meio do filtro de Mahalanobis modificado. Os resultados foram interpretados por meio da análise de agioipamento, análise das componentes principais e análise discriminante. O horizonte temporal das cerâmicas foi verificado por meio de técnicas de datação tennoluminescência (TL). Os resultados obtidos neste trabalho, em associação com infonnações oriundas da Arqueologia, pennitiram a identificação dos gi-upos cerâmicos correspondentes às ocupações ceramistas no sítio Justino e a definição de gi\'upos cerâmicos de referência confonne o comportamento químico. A tecnologia de queima foi estabelecida para alguns vasos cerâmicos, bem como a contemporaneidade dos grupos composicionais segundo as datações determinadas por TL. Dessa forma, o trabalho contribui para a reconstituição da pré-história das comunidades que habitaram a região do Baixo Rio São Francisco e para remontagem do quadro geral das populações ceramistas do Nordeste brasileiro. / The study of the physical and chemical characteristics of the ceramics crafts, in association with historical and archaeological research, has allowed for the reconstruction of the cultural habits from ancient communities. The goal of this work was to study the chemical and mineralogical compositions of archaeological potteries collected from Justino, São José, Curituba, Saco da Onça, Porto Belo and Vitória Régia sites, located in Baixo São Francisco region, Sergipe state, Brazil. The use of the instrumental neutron activation analysis (INAA) and X-ray diffractometry (XRD), allowed the definition of compositional groups of potteries according to the chemical similarities of the ceramic paste, which reveals the composition of the raw materials utilized in the manufacturing process by prehistoric man, and the inference of the atmosphere and temperatures in which the potteries were burned. The outliers were identified by means of classic and robust Mahalanobis distance. The temper effect in the ceramic paste was studied by means of modified Mahalanobis filter. The results were interpreted by means of cluster analysis, principal components analysis and discriminant analysis. The ages of some potteries were determined by means of the thermoluminescence techniques. The results obtained in this work, in association with archaeological information, allowed for the identification of the ceramic groups relative to ceramist occupations at Justino Site and for the definition of the reference groups according to the chemical composition. The burning technology was established for some potteries and the relative ages among the compositional groups were determined by means of TL. Thus, this work provides contributions to the reconstmction of the prehistory of the communities which lived in the Baixo São Francisco region, and to the reconstitution of the general frame of the ceramist population from Brazilian Northeast.

Excavated osteological material has been very valuable tool to reconstitute the more precise and objective view of the horses farmed in the past, to follow the evolution of the Lithuanian horse. The data that enabled to estimate the height, constitution and age of the horse is very rare. The metacarpal, metatarsal bones and scull or at least the lower jaw (mandibule) with teeth could be pointed out as the most valuable material. Teeth belong to the best preserved elements of excavations’ material. Such factors as dentition or wear allow determining the animal age. However solitary molars (as they found frequently) do not able to provide this kind of information. Therefore, the methods allowing determining the horse age according to the tooth height and number of cementum rings are very valuable.