miladh

• Djenouri, Youcef; Hjelmervik, Jon M.; Bjorne, Elias & Mobarhan, Milad (2022). How Image Retrieval and Matching Can Improve Object Localisation on Offshore Platforms. I Yin, Hujun; Camacho, David & Tino, Peter (Red.), Intelligent Data Engineering and Automated Learning – IDEAL 2022: 23rd International Conference, IDEAL 2022, Manchester, UK, November 24–26, 2022, Proceedings. ACM Publications. ISSN 978-3-031-21752-4. s. 262–270. doi: 10.1007/978-3-031-21753-1_26.
• Djenouri, Youcef; Hatleskog, Johan; Hjelmervik, Jon M.; Bjorne, Elias; Utstumo, Trygve & Mobarhan, Milad (2021). Deep learning based decomposition for visual navigation in industrial platforms. Applied intelligence (Boston). ISSN 0924-669X. doi: 10.1007/s10489-021-02908-z. Fulltekst i vitenarkiv Vis sammendrag

  In the heavy asset industry, such as oil & gas, offshore personnel need to locate various equipment on the installation on a daily basis for inspection and maintenance purposes. However, locating equipment in such GPS denied environments is very time consuming due to the complexity of the environment and the large amount of equipment. To address this challenge we investigate an alternative approach to study the navigation problem based on visual imagery data instead of current ad-hoc methods where engineering drawings or large CAD models are used to find equipment. In particular, this paper investigates the combination of deep learning and decomposition for the image retrieval problem which is central for visual navigation. A convolutional neural network is first used to extract relevant features from the image database. The database is then decomposed into clusters of visually similar images, where several algorithms have been explored in order to make the clusters as independent as possible. The Bag-of-Words (BoW) approach is then applied on each cluster to build a vocabulary forest. During the searching process the vocabulary forest is exploited to find the most relevant images to the query image. To validate the usefulness of the proposed framework, intensive experiments have been carried out using both standard datasets and images from industrial environments. We show that the suggested approach outperforms the BoW-based image retrieval solutions, both in terms of computing time and accuracy. We also show the applicability of this approach on real industrial scenarios by applying the model on imagery data from offshore oil platforms.

• Born, Gregory; Schneider-Soupiadis, Felix A.; Erisken, Sinem; Vaiceliunaite, Agne; Lao, Chu Lan & Mobarhan, Milad [Vis alle 9 forfattere av denne artikkelen] (2021). Corticothalamic feedback sculpts visual spatial integration in mouse thalamus. Nature Neuroscience. ISSN 1097-6256. 24, s. 1711–1720. doi: 10.1038/s41593-021-00943-0.
• Lepperød, Mikkel Elle; Dragly, Svenn-Arne; Buccino, Alessio Paolo; Mobarhan, Milad; Malthe-Sørenssen, Anders & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2020). Experimental Pipeline (Expipe): A Lightweight Data Management Platform to Simplify the Steps From Experiment to Data Analysis. Frontiers in Neuroinformatics. ISSN 1662-5196. 14. doi: 10.3389/fninf.2020.00030. Fulltekst i vitenarkiv Vis sammendrag

  As experimental neuroscience is moving toward more integrative approaches, with a variety of acquisition techniques covering multiple spatiotemporal scales, data management is becoming increasingly challenging for neuroscience laboratories. Often, datasets are too large to practically be stored on a laptop or a workstation. The ability to query metadata collections without retrieving complete datasets is therefore critical to efficiently perform new analyses and explore the data. At the same time, new experimental paradigms lead to constantly changing specifications for the metadata to be stored. Despite this, there is currently a serious lack of agile software tools for data management in neuroscience laboratories. To meet this need, we have developed Expipe, a lightweight data management framework that simplifies the steps from experiment to data analysis. Expipe provides the functionality to store and organize experimental data and metadata for easy retrieval in exploration and analysis throughout the experimental pipeline. It is flexible in terms of defining the metadata to store and aims to solve the storage and retrieval challenges of data/metadata due to ever changing experimental pipelines. Due to its simplicity and lightweight design, we envision Expipe as an easy-to-use data management solution for experimental laboratories, that can improve provenance, reproducibility, and sharing of scientific projects.

• Dragly, Svenn-Arne; Mobarhan, Milad; Lepperød, Mikkel Elle; Tennøe, Simen; Fyhn, Marianne & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2018). Experimental directory structure (Exdir): An alternative to HDF5 without introducing a new file format. Frontiers in Neuroinformatics. ISSN 1662-5196. 12. doi: 10.3389/fninf.2018.00016.
• Mobarhan, Milad; Halnes, Geir; Martínez-Cañada, Pablo; Hafting, Torkel; Fyhn, Marianne & Einevoll, Gaute (2018). Firing-rate based network modeling of the dLGN circuit: Effects of cortical feedback on spatiotemporal response properties of relay cells. PLoS Computational Biology. ISSN 1553-734X. 14(5). doi: 10.1371/journal.pcbi.1006156. Fulltekst i vitenarkiv
• Martínez-Cañada, Pablo; Mobarhan, Milad; Halnes, Geir; Fyhn, Marianne; Morillas, Christian & Pelayo, Francisco [Vis alle 7 forfattere av denne artikkelen] (2018). Biophysical network modeling of the dLGN circuit: Effects of cortical feedback on spatial response properties of relay cells. PLoS Computational Biology. ISSN 1553-734X. 14(1), s. 1–45. doi: 10.1371/journal.pcbi.1005930. Fulltekst i vitenarkiv
• Dragly, Svenn-Arne; Mobarhan, Milad; Solbrå, Andreas Våvang; Tennøe, Simen; Hafreager, Anders & Malthe-Sørenssen, Anders [Vis alle 9 forfattere av denne artikkelen] (2017). Neuronify: An educational simulator for neural circuits. eNeuro. ISSN 2373-2822. 4(2:e0022-17.2017), s. 1–13. doi: 10.1523/ENEURO.0022-17.2017. Fulltekst i vitenarkiv

Se alle arbeider i Cristin

• Røe, Malin Benum; Aasebø, Ida Elisabeth Jørgensen; Mobarhan, Milad; Lensjø, Kristian Kinden; Einevoll, Gaute & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2019). Stable orientation tuning in the freely moving rat: Movement-robust orientation-selective neurons in the deep layers of the primary visual cortex.
• Røe, Malin Benum; Aasebø, Ida Elisabeth Jørgensen; Mobarhan, Milad; Lensjø, Kristian Kinden; Einevoll, Gaute & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2019). Stable orientation tuning in the freely moving rat: Movement-robust orientation-selective neurons in the deep layers of the primary visual cortex.
• Røe, Malin Benum; Aasebø, Ida Elisabeth Jørgensen; Mobarhan, Milad; Lensjø, Kristian Kinden; Stöber, Tristan Manfred & Einevoll, Gaute [Vis alle 8 forfattere av denne artikkelen] (2018). Stable orientation tuning in the freely moving rat: Movement-robust orientation-selective neurons in the deep layers of the primary visual cortex.
• Dragly, Svenn-Arne; Mobarhan, Milad; Lepperød, Mikkel Elle; Tennøe, Simen; Stasik, Alexander Johannes & Fyhn, Marianne [Vis alle 8 forfattere av denne artikkelen] (2018). Exdir An alternative to HDF5 that uses Numpy files for data, YAML for metadata and simple directories to define the hierarchy.
• Stasik, Alexander Johannes; Mobarhan, Milad; Hagen, Espen & Einevoll, Gaute (2018). Generating Input from LGN for Simulation of Visual Cortex.
• Røe, Malin Benum; Aasebø, Ida Elisabeth Jørgensen; Mobarhan, Milad; Lensjø, Kristian Kinden; Einevoll, Gaute & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2018). Stable orientation tuning in the freely moving rat: Movement-robust orientation selective neurons in the deep layers of the primary visual cortex.
• Aasebø, Ida Elisabeth Jørgensen; Røe, Malin Benum; Mobarhan, Milad; Lensjø, Kristian Kinden; Stöber, Tristan Manfred & Einevoll, Gaute [Vis alle 8 forfattere av denne artikkelen] (2018). Orientation selectivity in the freely moving rat: Movement-robust orientation-selectivity (MROS) of units in the deep layers of the rat visual cortex .
• Røe, Malin Benum; Aasebø, Ida Elisabeth Jørgensen; Mobarhan, Milad; Lensjø, Kristian Kinden; Einevoll, Gaute & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2018). Movement-resistant orientation selectivity of cells in the deep layers of the rat visual cortex.
• Mobarhan, Milad; Halnes, Geir; Martínez-Cañada, Pablo; Hafting, Torkel; Fyhn, Marianne & Einevoll, Gaute (2017). Firing-rate Based Network Modeling of the dLGN Circuit: Effects of Cortical Feedback on Spatiotemporal Response Properties of Relay Cells .
• Dragly, Svenn-Arne; Mobarhan, Milad; Solbrå, Andreas Våvang; Tennøe, Simen; Hafreager, Anders & Malthe-Sørenssen, Anders [Vis alle 9 forfattere av denne artikkelen] (2017). Neuronify: An Educational Simulator for Neural Circuits. Vis sammendrag

  Neurons are cells in the brain that are able to rapidly change the electric field across their cell membrane. These changes allow neurons to communicate with each other and is the basis for the complex computations in the brain. Understanding how neurons communicate and the properties of neuronal networks is essential for neuroscience students. Traditionally, students draw networks with pen and paper and qualitatively deduce features of the network by analyzing the static drawings. Here, we present Neuronify, an app that allows students to draw the same networks on a computer or mobile device and run dynamic simulations without programming. The students can test their analysis by running the network and check their predictions against the outcome. Educational software (apps) can improve science education by providing an interactive way of learning about complicated topics that are hard to explain with text and static illustrations. Such software is readily available in many areas of natural science such as physics and electrical engineering. However, few educational apps are available for simulation of neural networks. Neuronify allows the user to easily create and explore neural networks in a plug-and-play simulation environment. The user can drag and drop network elements such as neurons, electrical stimulation tools and recording devices. The components can then easily be connected to one another. Building intuition for how neurons and neural networks behave has been a top priority in designing Neuronify. We aim to provide a low entry point to simulation-based neuroscience. Most undergraduate students do not have the computational experience to create their own neural simulator. Neuronify offers them an opportunity to build and experiment with neural networks in a graphical and easy-to-understand interface. By playing around with the networks, the students can develop a good understanding of their properties. To facilitate the use of Neuronify in teaching, a set of premade common network motifs is provided, performing functions such as input summation and detection of direction of stimulus movement. Neuronify is developed in C++ and QML using the cross-platform application framework Qt. It has been downloaded more than 30,000 times since its launch and is available on smart phones (Android, iOS), tablet computers as well personal computers (Windows, Mac, Linux).

• Tennøe, Simen; Mobarhan, Milad; Dragly, Svenn-Arne; Solbrå, Andreas Våvang & Nederbragt, Alexander Johan (2017). Teaching modelling to first-year biology students. Vis sammendrag

  The field of biology relies heavily on computations. This is not well reflected in education and the current undergraduate curriculum has little computational content. This results in a discontinuity between the education received by the students and the problems they face after graduation. The end result is that the students are not equipped to meet the requirements of modern research nor the tasks awaiting them in the industry. To remedy this problem, a new course, BIOS 1100 - Introduction to Modelling in Biology, will be held for the first time at the University of Oslo in fall 2017. Currently, no available book combines biology and programming at an introductory level in a satisfactory way. Most textbooks teach both topics separately or expect the reader to know either biology or programming from before. We have therefore written our own textbook to be used as curriculum in this course. This book aims to teach programming and modelling to first year biology students through examples from biology. The book is based on a philosophy of just-in-time teaching where the programming concepts are introduced just when they are needed to solve the problem in hand. This puts the programming content in an unusual order in comparison to the traditional computer science curriculum while keeping the biology students motivated by the problems they solve. The examples are mainly from the three branches of biology: population dynamics, bioinformatics and evolution. The purpose is to give biology students a practical understanding of programming and mathematical models. This will enable the understanding of mathematical models and encourage critical thinking. Programming allows much more realistic and inspiring problems to be addressed, enabling students to work on current research topics early on. The textbook is written using DocOnce (created by Hans Petter Langtangen), which enables us to compile the book to both LaTeX/PDF, HTML and Jupyter Notebooks.

• Aasebø, Ida E. J.; Mobarhan, Milad; Røe, Malin Benum; Lensjø, Kristian Kinden; Einevoll, Gaute & Hafting, Torkel [Vis alle 7 forfattere av denne artikkelen] (2017). Movement-resistant orientation-selective units in the deep layers of the visual cortex.
• Dragly, Svenn-Arne; Mobarhan, Milad; Solbrå, Andreas Våvang & Tennøe, Simen (2016). Neuronify: An educational app for simulation of neural circuits.
• Mobarhan, Milad; Dragly, Svenn-Arne & Solbrå, Andreas Våvang (2016). Neuronify: an educational app for simulation of neural circuits.
• Mobarhan, Milad; Tennøe, Simen & Solbrå, Andreas Våvang (2016). Neuronify: a new tool for creating simple neural networks .
• Mobarhan, Milad; Dragly, Svenn-Arne; Tennøe, Simen & Solbrå, Andreas Våvang (2016). Introduction to Computational Biology with Python .
• Tennøe, Simen; Mobarhan, Milad; Dragly, Svenn-Arne; Solbrå, Andreas Våvang & Langtangen, Hans Petter (2015). CSE: Computing in Science Education.
• Hobbi Mobarhan, Milad; Einevoll, Gaute; Geir, Halnes; Vervaeke, Koen Gerard Alois & Fyhn, Marianne (2015). Roles of cortical feedback in lateral geniculate nucleus.

Se alle arbeider i Cristin