The paper shows several methods employed in a semi-automatic pipeline for 3D surface reconstruction of anatomic shapes from Computed Tomography scans. Main benefits of the approach are very little human involvement an...
详细信息
The paper shows several methods employed in a semi-automatic pipeline for 3D surface reconstruction of anatomic shapes from Computed Tomography scans. Main benefits of the approach are very little human involvement and high processing speed, while maintaining high reconstruction accuracy. Several filtering methods are described that make contour segmentation easier. Further improvements of the algorithm are proposed.
Visual perception capabilities are still highly unreliable in unconstrained settings, and solutions might not be accurate in all regions of an image. Awareness of the uncertainty of perception is a fundamental require...
详细信息
We propose a distributed learning algorithm for fair scheduling in common-pool games. Common-pool games are strategic-form games where multiple agents compete over utilizing a limited common resource. A characteristic...
详细信息
Multimedia is one of the most important aspects of the information era. With the advent of the multimedia age and the spread of Internet, video storage and streaming has been gaining a lot of popularity. When transmit...
详细信息
Multimedia is one of the most important aspects of the information era. With the advent of the multimedia age and the spread of Internet, video storage and streaming has been gaining a lot of popularity. When transmitting compressed video over a data network channel errors affect the decoding process. Video transmission puts constraints on data rate, computational complexity and delay. Unreliable channels add more challenges to this task as compressed video is extremely vulnerable to transmission errors. Problems arising from imperfect transmission of block coded video frame sequence result in lost blocks. This paper presents and implements a set of decoder side spatio-temporal algorithms that aim to enhance the speed and quality of the error concealment process. The results obtained by these algorithms are much faster and achieve better performance compared to the existing algorithms, which make them more suitable for real-time applications.
Some have argued that the dichotomy between high-performance operation and low resource utilization is false - an artifact that will soon succumb to Moore's Law and careful engineering. If such claims prove to be ...
详细信息
To research the effects of electric power steering (EPS) system on vehicle handling stability and to improve it, this paper derives the expressions of road feeling and steering sensitivity, regards which as the perfor...
详细信息
In this paper, we propose a cooperative localization algorithm for mobile sensor networks with camera sensors to operate under GPS denied areas or indoor environments. Mobile robots are partitioned into two groups. On...
详细信息
作者:
Ivars KarpicsInstitute of computer control
automation and computer engineering Faculty of computer science and information technology Riga Technical University Riga Latvia
In the article a therapy selection method by using topological modelling and multi- objective optimization is presented. In a medicine practice a doctor by taking into the count patients' health state and laborato...
详细信息
In the article a therapy selection method by using topological modelling and multi- objective optimization is presented. In a medicine practice a doctor by taking into the count patients' health state and laboratory results, tries to suggest a treatment strategy, which mostly is a drug therapy. To solve this task a decision support system has been developed and proposed. The system includes a mathematical model of three self connected diseases. Therapies are evaluated by five efficiency objectives. To find the optimal therapy, seven multi- objective methods are selected and used. Optimization methods form decision support module which is implemented in the medical computer system. To evaluate a performance of the system, test examples are analysed. Conclusion includes the summary and proposals of further research.
In this paper we deal with a companion that is capable of migration to variety of embodiments in order to fulfil its tasks (including the social one) and to achieve its goals. It is important that identity of a compan...
详细信息
In this paper we deal with a companion that is capable of migration to variety of embodiments in order to fulfil its tasks (including the social one) and to achieve its goals. It is important that identity of a companion in each utilised embodiment can be recognised by the user regardless technological constraints and own capabilities of a robotic platform. We are focused on the case when one companion uses two robots, embodied in different degrees, whereby one robot is poorly embodied. In this context the concept of unfalsified identity is introduced. In video-based user studies the less embodied robot companion reveals a certain set of characteristic behaviours relevant the context and the currently carried out task. These behaviours are consistent with behaviours observed by the user earlier, in similar contexts, when the companion was more embodied. It follows from the study that the user can properly recognise the identity of this companion with a certain level of confidence. A number of observations relevant to behaviours as identity cues are presented and discussed.
A variant of spiking neural P systems was recently investigated by the authors, using astrocytes that have excitatory and inhibitory influence on synapses. In this work, we consider this system in the non-synchronized...
详细信息
暂无评论