Codebook-based electrooculography data analysis towards cognitive activity recognition.

With the advancement in mobile/wearable technology, people started to use a variety of sensing devices to track their daily activities as well as health and fitness conditions in order to improve the quality of life. This work addresses an idea of eye movement analysis, which due to the strong correlation with cognitive tasks can be successfully utilized in activity recognition. Eye movements are recorded using an electrooculographic (EOG) system built into the frames of glasses, which can be worn more unobtrusively and comfortably than other devices. Since the obtained information is low-level sensor data expressed as a sequence representing values in constant intervals (100 Hz), the cognitive activity recognition problem is formulated as sequence classification. However, it is unclear what kind of features are useful for accurate cognitive activity recognition. Thus, a machine learning algorithm like a codebook approach is applied, which instead of focusing on feature engineering is using a distribution of characteristic subsequences (codewords) to describe sequences of recorded EOG data, where the codewords are obtained by clustering a large number of subsequences. Further, statistical analysis of the codeword distribution results in discovering features which are characteristic to a certain activity class. Experimental results demonstrate good accuracy of the codebook-based cognitive activity recognition reflecting the effective usage of the codewords.

Skeleton Graph Matching vs. Maximum Weight Cliques aorta registration techniques.

Vascular diseases are one of the most challenging health problems in developed countries. Past as well as ongoing research activities often focus on efficient, robust and fast aorta segmentation, and registration techniques. According to this needs our study targets an abdominal aorta registration method. The investigated algorithms make it possible to efficiently segment and register abdominal aorta in pre- and post-operative Computed Tomography (CT) data. In more detail, a registration technique using the Path Similarity Skeleton Graph Matching (PSSGM), as well as Maximum Weight Cliques (MWCs) are employed to realise the matching based on Computed Tomography data. The presented approaches make it possible to match characteristic voxels belonging to the aorta from different Computed Tomography (CT) series. It is particularly useful in the assessment of the abdominal aortic aneurysm treatment by visualising the correspondence between the pre- and post-operative CT data. The registration results have been tested on the database of 18 contrast-enhanced CT series, where the cross-registration analysis has been performed producing 153 matching examples. All the registration results achieved with our system have been verified by an expert. The carried out analysis has highlighted the advantage of the MWCs technique over the PSSGM method. The verification phase proves the efficiency of the MWCs approach and encourages to further develop this methods.

Skeleton-based abdominal aorta registration technique.

Vascular diseases are the most challenging health problems in developed countries. The vascular segmentation as well as registration techniques are the topics of past and ongoing research activities. In this work we target an abdominal aorta registration technique. The developed methodology is useful in the assessment of abdominal aortic aneurysm treatment by visualizing the correspondence between pre- and postoperative Computed Tomography (CT) data. The presented approach makes it possible to match all voxels belonging to the aorta from different CT series. It is based on aorta lumen segmentation and graph matching method. To segment the lumen area a hybrid level-set active contour approach is used. The matching step is performed based on a path similarity skeleton graph matching procedure. The registration results have been tested on the database of 8 patients, for which two different contrast-enhanced CT series were acquired. All registration results achieved with our system and verified by an expert prove the efficiency of the approach and encourage to further develop this method.