A distribuição, composição e alguns aspectos da variação temporal de grande escala da macrofauna bentônica da zona costeira rasa da baía do Almirantado já são conhecidos. O presente trabalho investigou a variação temporal de pequena escala da macrofauna, com ênfase nos Polychaeta, aos 20 metros de profundidade na enseada Martel. Foram feitas amostragens de sedimento, com um pegador de fundo tipo van Veen, em um mesmo ponto durante 35 dias, em intervalos aproximados de uma semana. Foram verificadas variações significativas na densidade de alguns grupos taxonômicos (Amphipoda e Polychaeta) e na composição granulométrica sedimentar. Bivalvia, Amphipoda, Cumacea e Oligochaeta, que vivem nas primeiras camadas do sedimento, constituíram um grupo sensível ao impacto causado por intensas tempestades. As espécies dominantes de Polychaeta (87% do total) foram Rhodine intermedia, Ophelina syringopige, O. gymnopyge, Apistobranchus glacierae e Tharyx cf. cincinnatus. Somente a densidade de O. gymnopyge apresentou variação significativa, o que não ocorreu com os descritores ecológicos do grupo. Estes resultados colaboram para o INCT-APA, fornecendo informações importantes para a interpretação dos dados obtidos no atual programa de monitoramento desenvolvido na baía do Almirantado. Este estudo integra o projeto do Ano Polar Internacional \"MABIREH\" e contribuirá para bases de dados \"SCAR-MarBin\" e \"ABBED\". / The distribution, composition and some aspects of long-term temporal variation of macrofauna from shallow waters of Admiralty Bay are reasonably well know. The present study aimed to investigate the short-term variation of macrofauna, with emphasis on Polychaeta, in Martel Inlet. Sediment was sampled, at 20 m depth, with a van Veen grab for approximately 35 days, almost every week. During the study period, significant variations were verified on the density of some taxa (Amphipoda and Polychaeta), as well as on the sediment composition. Bivalvia, Amphipoda, Cumacea and Oligochaeta at the first sediment layers were more susceptible to the impact of the severe storms. The dominant species of Polychaeta were Rhodine intermedia, Ophelina syringopyge, O. gymnopyge, Apistobranchus glacierae and Tharyx cf. cincinnatus, counting for 87% of the total group. The density of Ophelina gymnopyge presented a significant short-term variation, however, ecological descriptors for Polychaeta assemblages did not vary at the same way. These results collaborate to the INCT-APA, by providing important information to interpret the acquired data about the environmental monitoring program developed in Admiralty Bay. This study is part of the International Polar Year project \"MABIREH\" and will integrate \"SCAR-MarBin\" and \"ABBED\" data bases.

A distribuição, composição e alguns aspectos da variação temporal de grande escala da macrofauna bentônica da zona costeira rasa da baía do Almirantado já são conhecidos. O presente trabalho investigou a variação temporal de pequena escala da macrofauna, com ênfase nos Polychaeta, aos 20 metros de profundidade na enseada Martel. Foram feitas amostragens de sedimento, com um pegador de fundo tipo van Veen, em um mesmo ponto durante 35 dias, em intervalos aproximados de uma semana. Foram verificadas variações significativas na densidade de alguns grupos taxonômicos (Amphipoda e Polychaeta) e na composição granulométrica sedimentar. Bivalvia, Amphipoda, Cumacea e Oligochaeta, que vivem nas primeiras camadas do sedimento, constituíram um grupo sensível ao impacto causado por intensas tempestades. As espécies dominantes de Polychaeta (87% do total) foram Rhodine intermedia, Ophelina syringopige, O. gymnopyge, Apistobranchus glacierae e Tharyx cf. cincinnatus. Somente a densidade de O. gymnopyge apresentou variação significativa, o que não ocorreu com os descritores ecológicos do grupo. Estes resultados colaboram para o INCT-APA, fornecendo informações importantes para a interpretação dos dados obtidos no atual programa de monitoramento desenvolvido na baía do Almirantado. Este estudo integra o projeto do Ano Polar Internacional \"MABIREH\" e contribuirá para bases de dados \"SCAR-MarBin\" e \"ABBED\". / The distribution, composition and some aspects of long-term temporal variation of macrofauna from shallow waters of Admiralty Bay are reasonably well know. The present study aimed to investigate the short-term variation of macrofauna, with emphasis on Polychaeta, in Martel Inlet. Sediment was sampled, at 20 m depth, with a van Veen grab for approximately 35 days, almost every week. During the study period, significant variations were verified on the density of some taxa (Amphipoda and Polychaeta), as well as on the sediment composition. Bivalvia, Amphipoda, Cumacea and Oligochaeta at the first sediment layers were more susceptible to the impact of the severe storms. The dominant species of Polychaeta were Rhodine intermedia, Ophelina syringopyge, O. gymnopyge, Apistobranchus glacierae and Tharyx cf. cincinnatus, counting for 87% of the total group. The density of Ophelina gymnopyge presented a significant short-term variation, however, ecological descriptors for Polychaeta assemblages did not vary at the same way. These results collaborate to the INCT-APA, by providing important information to interpret the acquired data about the environmental monitoring program developed in Admiralty Bay. This study is part of the International Polar Year project \"MABIREH\" and will integrate \"SCAR-MarBin\" and \"ABBED\" data bases.

We propose a running example for heterogeneous approach based on new type of fuzzification that diversifies fuzziness of every object, fuzziness of every attribute and fuzziness of every table value in a formal context. Moreover we suggest another working examples on heterogeneous environment and provide additional utilization and illustration of this new model that allows to use Formal Concept Analysis also for heterogenenous data. An interpretation of heterogeneous formal concepts and the resulting concept lattice is included.

We propose a running example for heterogeneous approach based on new type of fuzzification that diversifies fuzziness of every object, fuzziness of every attribute and fuzziness of every table value in a formal context. Moreover we suggest another working examples on heterogeneous environment and provide additional utilization and illustration of this new model that allows to use Formal Concept Analysis also for heterogenenous data. An interpretation of heterogeneous formal concepts and the resulting concept lattice is included.

A modular Recurrent Bayesian Confidence PropagatingNeural Networks (BCPNN) with two synaptic time tracesis a computational neural network that can serve as a modelof biological short term memory. The units in the network aregrouped into modules called hypercolumns within which there isa competitive winner-takes-all mechanism.In this work, the network’s capacity to store sequentialmemories is investigated while varying the size of and numberof hyperocolumns in the network. The network is trained on setsof temporal sequences where each sequence consist of a set ofsymbols represented as semi-stable attractor state patterns in thenetwork and evaluated by its ability to later recall the sequences.For a given distribution of training sequence the networks’ability to store and recall sequences was seen to significantlyincrease with the size of the hypercolumns. As the number ofhypercolumns was increased, the storage capacity increased upto a clear level in most cases. After this point it was observedto remain constant and did not improve by adding any morehypercolumns (for a given sequence distribution). The storagecapacity was also seen to depend a lot on the distribution of thesequences. / Ett modulärt Recurrent Bayesian Confidence Propagating Neural Network (BCPNN) med två synaptiskatidsspår är ett neuronnät som kan användas som en modell förbiologiskt korttidsminne. Enheterna i nätverket är grupperade imoduler kallade hyperkolumner inom vilka enheterna konkurrerarenligt en ”winner-takes-all”-mekanism.I det här arbetet undersöktes hur nätverkets förmåga attlagra sekventiella minnen beror på storleken och antalet hyperkolumner.Nätverket tränades på ett antal temporala följderdär varje följd bestod av en mängd symboler som representeradesom attraktor-tillstånd i nätverket och bedömdes baserat på dessförmåga att komma ihåg följder det lärt sig under träning.För en given fördelning av träningsföljder ökade nätverketsförmåga att lagra och återkalla följder med storleken på hyperkolumnerna.Då antalet hyperkolumner ökades ökade ocks i de flesta fall lagringsförmågan upp till en viss nivå varefterytterligare hyperkolumner inte gav några vidare förbättringar(för en given fördelning av sekvenser). Lagringskapacitetenberodde också mycket på fördelningen av följder. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

Knowledge tracing is concerned with tracking a student’s knowledge as she/he engages with exercises in an (online) learning platform. A commonly used state-of-theart knowledge tracing model is Deep Knowledge Tracing (DKT) which models the time dimension as a sequence of completed exercises per student by using a Long Short-Term Memory Neural Network (LSTM). However, a common problem in this sequence-based model is too much instability in the time dimension of the modelled knowledge of a student. In other words, the student’s knowledge on a skill changes too quickly and unreliably. We propose dynamic student embeddings as a stable method for encoding the time dimension of knowledge tracing systems. In this method the time dimension is encoded in time slices of a fixed size, while the model’s loss function is designed to smoothly align subsequent time slices. We compare the dynamic student embeddings to DKT on a large-scale real-world dataset, and we show that dynamic student embeddings provide a more stable knowledge tracing while retaining good performance. / Kunskapsspårning handlar om att modellera en students kunskaper då den arbetar med uppgifter i en (online) lärplattform. En vanlig state-of-the-art kunskapsspårningsmodell är Deep Knowledge Tracing (DKT) vilken modellerar tidsdimensionen som en sekvens av avslutade uppgifter per student med hjälp av ett neuronnät kallat Long Short-Term Memory Neural Network (LSTM). Ett vanligt problem i dessa sekvensbaserade modeller är emellertid en för stor instabilitet i tidsdimensionen för studentens modellerade kunskap. Med andra ord, studentens kunskaper förändras för snabbt och otillförlitligt. Vi föreslår därför Dynamiska Studentvektorer som en stabil metod för kodning av tidsdimensionen för kunskapsspårningssystem. I denna metod kodas tidsdimensionen i tidsskivor av fix storlek, medan modellens förlustfunktion är utformad för att smidigt justera efterföljande tidsskivor. I denna uppsats jämför vi de Dynamiska Studentvektorer med DKT i en storskalig verklighetsbaserad dataset, och visar att Dynamiska Studentvektorer tillhandahåller en stabilare kunskapsspårning samtidigt som prestandan bibehålls.