Maksims Ivanovs

Maksims Ivanovs
Elektronikas un datorzinātņu institūts

About

8
Publications
17,268
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
16
Citations

Publications

Publications (8)
Article
Full-text available
Semantic segmentation of an incoming visual stream from cameras is an essential part of the perception system of self-driving cars. State-of-the-art results in semantic segmentation have been achieved with deep neural networks (DNNs), yet training them requires large datasets, which are difficult and costly to acquire and time-consuming to label. A...
Article
Full-text available
Deep neural networks (DNNs) have achieved state-of-the-art results in a broad range of tasks, in particular the ones dealing with the perceptual data. However, full-scale application of DNNs in safety-critical areas is hindered by their black box-like nature, which makes their inner workings nontransparent. As a response to the black box problem, t...
Article
Full-text available
Washing hands is one of the most important ways to prevent infectious diseases, including COVID-19. The World Health Organization (WHO) has published hand-washing guidelines. This paper presents a large real-world dataset with videos recording medical staff washing their hands as part of their normal job duties in the Pauls Stradins Clinical Univer...
Preprint
Washing hands is one of the most important ways to prevent infectious diseases, including COVID-19. Unfortunately, medical staff does not always follow the World Health Organization (WHO) hand washing guidelines in their everyday work. To this end, we present neural networks for automatically recognizing the different washing movements defined by t...
Preprint
Due to breakthroughs in embedded system development, sensing technologies, and ubiquitous connectivity in recent years, technologies such as Wireless Sensor Networks (WSN) and Internet of Things (IoT) have captured the imagination of researchers, businesses, and general public. That resulted in the emergence of an enormous, difficult-to-navigate bo...

Questions

Questions (3)
Question
Dear all,
I had been wondering whether someone happens to know any publications (e.g. review articles) offering an overview of the methods, in particular visual stimuli, used to map visual receptive fields. There have been a number of such stimuli used for that purpose, e.g. drifting grating or flashing spots, yet I could not find an overview of of them so far, so any hints would be much appreciated.
Thanks a lot in advance!
Max
Question
Hello, 
I have a problem with the cryoprotection of mouse hippocampal slices. The samples are PFA-fixated and cryoprotected in 30 % sucrose in PBS solution; they would normally sink to the bottom of their wells in the 96-well plate after a couple of days in the cryoprotectant, but this time none of the samples (there are five of them all in all) would sink. I have already encountered such a problem a couple of times before, and according to my experience it is not a good idea to proceed with samples that are still floating, as that implies that they have not been cryoprotected well enough and therefore are very likely to get damaged during sectioning.
I placed them on a shaker in a cold room now, as I hope that that would help the cryoprotectant to enter the samples; however, I am not sure that that would work. Therefore, any advice would be very appreciated. 
Thanks a lot in advance! 
Max
Question
Hello all, 
Some advice regarding cryosectioning would be highly appreciated. I am working with samples of the mouse hippocampus (NB! not the full brain, just the hippocampus, so they are rather small). My goal is to cut them into 30 μm thick sections and stain them with Nissl staining afterwards. The samples are PFA-fixated, cryoprotected in 30 % sucrose in PBS solution, and then embedded in NEG 50 embedding medium prior to cryosectioning. The problem is that in great many cases, the cryostat cuts the embedding medium smoothly, but as soon as the sample itself is reached, a hole appears in it. Sometimes the hole just damages the sample badly, in worst cases the sample is torn out of the section completely, and there is nothing much to stain. I have tried changing the temperature of the chamber and the knife (-12/-15, -11/-14, and -10/-13 degrees, respectively) as well as replaced the knife, but nothing really helps.
Thanks a lot in advance for your suggestions!