mdh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 174) Show all publications
Loni, M., Hamouachy, F., Casarrubios, C., Daneshtalab, M. & Nolin, M. (2019). AutoRIO: An Indoor Testbed for Developing Autonomous Vehicles. In: International Japan-Africa Conference on Electronics, Communications and Computations JAC-ECC: . Paper presented at International Japan-Africa Conference on Electronics, Communications and Computations JAC-ECC, 16 Dec 2018, Alexandria, Egypt (pp. 69-72).
Open this publication in new window or tab >>AutoRIO: An Indoor Testbed for Developing Autonomous Vehicles
Show others...
2019 (English)In: International Japan-Africa Conference on Electronics, Communications and Computations JAC-ECC, 2019, p. 69-72Conference paper, Published paper (Refereed)
Abstract [en]

Autonomous vehicles have a great influence on our life. These vehicles are more convenient, more energy efficient providing higher safety level and cheaper driving solutions. In addition, decreasing the generation of CO 2 , and the risk vehicular accidents are other benefits of autonomous vehicles. However, leveraging a full autonomous system is challenging and the proposed solutions are newfound. Providing a testbed for evaluating new algorithms is beneficial for researchers and hardware developers to verify the real impact of their solutions. The existence of testing environment is a low-cost infrastructure leading to increase the time-to-market of novel ideas. In this paper, we propose Auto Rio, a cutting-edge indoor testbed for developing autonomous vehicles.

National Category
Engineering and Technology Computer Systems
Identifiers
urn:nbn:se:mdh:diva-42236 (URN)10.1109/JEC-ECC.2018.8679543 (DOI)000465120800017 ()2-s2.0-85064611063 (Scopus ID)9781538692301 (ISBN)
Conference
International Japan-Africa Conference on Electronics, Communications and Computations JAC-ECC, 16 Dec 2018, Alexandria, Egypt
Projects
DPAC - Dependable Platforms for Autonomous systems and Control
Available from: 2018-12-28 Created: 2018-12-28 Last updated: 2019-05-09Bibliographically approved
Loni, M., Zoljodi, A., Seenan, S., Daneshtalab, M. & Nolin, M. (2019). NeuroPower: Designing Energy Efficient Convolutional Neural Network Architecture for Embedded Systems. In: The 28th International Conference on Artificial Neural Networks ICANN 2019: . Paper presented at The 28th International Conference on Artificial Neural Networks ICANN 2019, 17 Sep 2019, Munich, Germany. Munich, Germany: Springer
Open this publication in new window or tab >>NeuroPower: Designing Energy Efficient Convolutional Neural Network Architecture for Embedded Systems
Show others...
2019 (English)In: The 28th International Conference on Artificial Neural Networks ICANN 2019, Munich, Germany: Springer , 2019Conference paper, Published paper (Refereed)
Abstract [en]

Convolutional Neural Networks (CNNs) suffer from energy-hungry implementation due to their computation and memory intensive processing patterns. This problem is even more significant by the proliferation of CNNs on embedded platforms. To overcome this problem, we offer NeuroPower as an automatic framework that designs a highly optimized and energy efficient set of CNN architectures for embedded systems. NeuroPower explores and prunes the design space to find improved set of neural architectures. Toward this aim, a multi-objective optimization strategy is integrated to solve Neural Architecture Search (NAS) problem by near-optimal tuning network hyperparameters. The main objectives of the optimization algorithm are network accuracy and number of parameters in the network. The evaluation results show the effectiveness of NeuroPower on energy consumption, compacting rate and inference time compared to other cutting-edge approaches. In comparison with the best results on CIFAR-10/CIFAR-100 datasets, a generated network by NeuroPower presents up to 2.1x/1.56x compression rate, 1.59x/3.46x speedup and 1.52x/1.82x power saving while loses 2.4%/-0.6% accuracy, respectively.

Place, publisher, year, edition, pages
Munich, Germany: Springer, 2019
Keywords
Convolutional neural networks (CNNs), Neural Architecture Search (NAS), Embedded Systems, Multi-Objective Optimization
National Category
Engineering and Technology Computer Systems
Identifiers
urn:nbn:se:mdh:diva-45043 (URN)
Conference
The 28th International Conference on Artificial Neural Networks ICANN 2019, 17 Sep 2019, Munich, Germany
Projects
DPAC - Dependable Platforms for Autonomous systems and ControlDeepMaker: Deep Learning Accelerator on Commercial Programmable Devices
Available from: 2019-08-23 Created: 2019-08-23 Last updated: 2019-08-23Bibliographically approved
Nazari, N., Loni, M., E. Salehi, M., Daneshtalab, M. & Nolin, M. (2019). TOT-Net: An Endeavor Toward Optimizing Ternary Neural Networks. In: 22nd Euromicro Conference on Digital System Design DSD 2019: . Paper presented at 22nd Euromicro Conference on Digital System Design DSD 2019, 28 Aug 2019, Chalkidiki, Greece.
Open this publication in new window or tab >>TOT-Net: An Endeavor Toward Optimizing Ternary Neural Networks
Show others...
2019 (English)In: 22nd Euromicro Conference on Digital System Design DSD 2019, 2019Conference paper, Published paper (Refereed)
Abstract [en]

High computation demands and big memory resources are the major implementation challenges of Convolutional Neural Networks (CNNs) especially for low-power and resource-limited embedded devices. Many binarized neural networks are recently proposed to address these issues. Although they have significantly decreased computation and memory footprint, they have suffered from accuracy loss especially for large datasets. In this paper, we propose TOT-Net, a ternarized neural network with [-1, 0, 1] values for both weights and activation functions that has simultaneously achieved a higher level of accuracy and less computational load. In fact, first, TOT-Net introduces a simple bitwise logic for convolution computations to reduce the cost of multiply operations. To improve the accuracy, selecting proper activation function and learning rate are influential, but also difficult. As the second contribution, we propose a novel piece-wise activation function, and optimized learning rate for different datasets. Our findings first reveal that 0.01 is a preferable learning rate for the studied datasets. Third, by using an evolutionary optimization approach, we found novel piece-wise activation functions customized for TOT-Net. According to the experimental results, TOT-Net achieves 2.15%, 8.77%, and 5.7/5.52% better accuracy compared to XNOR-Net on CIFAR-10, CIFAR-100, and ImageNet top-5/top-1 datasets, respectively.

Keywords
convolutional neural networks, ternary neural network, activation function, optimization
National Category
Engineering and Technology Computer Systems
Identifiers
urn:nbn:se:mdh:diva-45042 (URN)
Conference
22nd Euromicro Conference on Digital System Design DSD 2019, 28 Aug 2019, Chalkidiki, Greece
Projects
DPAC - Dependable Platforms for Autonomous systems and ControlDeepMaker: Deep Learning Accelerator on Commercial Programmable Devices
Available from: 2019-08-23 Created: 2019-08-23 Last updated: 2019-08-23Bibliographically approved
Tsog, N., Sjödin, M. & Bruhn, F. (2018). Advancing On-Board Big Data Processing Using Heterogeneous System Architecture. In: ESA/CNES 4S Symposium 4S 2018: . Paper presented at ESA/CNES 4S Symposium 4S 2018, 28 May 2018, Sorrento, Italy.
Open this publication in new window or tab >>Advancing On-Board Big Data Processing Using Heterogeneous System Architecture
2018 (English)In: ESA/CNES 4S Symposium 4S 2018, 2018Conference paper, Poster (with or without abstract) (Refereed)
Keywords
Heterogeneous System Architecture (HSA)Onboard ProcessingBig DataCPU-GPUCaffe (Convolutional Architecture for Fast Feature Embedding)ROCmSmall SatelliteCubeSatImagenet
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-39269 (URN)
Conference
ESA/CNES 4S Symposium 4S 2018, 28 May 2018, Sorrento, Italy
Projects
DPAC - Dependable Platforms for Autonomous systems and Control
Available from: 2018-05-23 Created: 2018-05-23 Last updated: 2018-05-23Bibliographically approved
Bucaioni, A., Cicchetti, A., Ciccozzi, F., Kodali, M. & Sjödin, M. (2018). Alignment of Requirements and Testing in Agile: An Industrial Experience. Advances in Intelligent Systems and Computing, 738, 225-232
Open this publication in new window or tab >>Alignment of Requirements and Testing in Agile: An Industrial Experience
Show others...
2018 (English)In: Advances in Intelligent Systems and Computing, ISSN 2194-5357, E-ISSN 2194-5365, Vol. 738, p. 225-232Article in journal (Refereed) Published
Abstract [en]

Agile development aims at switching the focus from processes to interactions between stakeholders, from heavy to minimalistic documentation, from contract negotiation and detailed plans to customer collaboration and prompt reaction to changes. With these premises, requirements traceability may appear to be an overly exigent activity, with little or no return-of-investment. However, since testing remains crucial even when going agile, the developers need to identify at a glance what to test and how to test it. That is why, even though requirements traceability has historically faced a firm resistance from the agile community, it can provide several benefits when promoting precise alignment of requirements with testing. This paper reports on our experience in promoting traceability of requirements and testing in the data communications for mission-critical systems in an industrial Scrum project. We define a semi-automated requirements tracing mechanism which coordinates four traceability techniques. We evaluate the solution by applying it to an industrial project aiming at enhancing the existing Virtual Router Redundancy Protocol by adding Simple Network Management Protocol support. 

Place, publisher, year, edition, pages
Springer Verlag, 2018
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-39196 (URN)10.1007/978-3-319-77028-4_33 (DOI)2-s2.0-85045853502 (Scopus ID)
Available from: 2018-05-11 Created: 2018-05-11 Last updated: 2018-05-11Bibliographically approved
Loni, M., Majd, A., Loni, A., Daneshtalab, M., Nolin, M. & Troubitsyna, E. (2018). Designing Compact Convolutional Neural Network for Embedded Stereo Vision Systems. In: IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip MCSoC-2018: . Paper presented at IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip MCSoC-2018, 12 Sep 2018, Hanoi, Vietnam (pp. 244-251). , Article ID 8540240.
Open this publication in new window or tab >>Designing Compact Convolutional Neural Network for Embedded Stereo Vision Systems
Show others...
2018 (English)In: IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip MCSoC-2018, 2018, p. 244-251, article id 8540240Conference paper, Published paper (Refereed)
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-40892 (URN)10.1109/MCSoC2018.2018.00049 (DOI)2-s2.0-85059750226 (Scopus ID)9781538666890 (ISBN)
Conference
IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip MCSoC-2018, 12 Sep 2018, Hanoi, Vietnam
Projects
DPAC - Dependable Platforms for Autonomous systems and ControlDeepMaker: Deep Learning Accelerator on Commercial Programmable Devices
Available from: 2018-09-18 Created: 2018-09-18 Last updated: 2019-01-17
Tsog, N., Behnam, M., Nolin, M. & Bruhn, F. (2018). Intelligent Data Processing using In-Orbit Advanced Algorithms on Heterogeneous System Architecture. In: IEEE Aerospace Conference 2018 IEEEAC2018: . Paper presented at IEEE Aerospace Conference 2018 IEEEAC2018, 03 Mar 2018, Big Sky, United States (pp. 1-8).
Open this publication in new window or tab >>Intelligent Data Processing using In-Orbit Advanced Algorithms on Heterogeneous System Architecture
2018 (English)In: IEEE Aerospace Conference 2018 IEEEAC2018, 2018, p. 1-8Conference paper, Published paper (Refereed)
Abstract [en]

In recent years, commercial exploitation of small satellites and CubeSats has rapidly increased. Time to market of processed customer data products is becoming an important differentiator between solution providers and satellite constellation operators. Timely and accurate data dissemination is the key to success in the commercial usage of small satellite constellations which is ultimately dependent on a high degree of autonomous fleet management and automated decision support. The traditional way for disseminating data is limited by on the communication capability of the satellite and the ground terminal availability. Even though cloud computing solutions on the ground offer high analytical performance, getting the data from the space infrastructure to the ground servers poses a bottleneck of data analysis and distribution. On the other hand, adopting advanced and intelligent algorithms onboard offers the ability of autonomy, tasking of operations, and fast customer generation of low latency conclusions, or even real-time communication with assets on the ground or other sensors in a multi-sensor configuration. In this paper, the advantages of intelligent onboard processing using advanced algorithms for Heterogeneous System Architecture (HSA) compliant onboard data processing systems are explored. The onboard data processing architecture is designed to handle a large amount of high-speed streaming data and provides hardware redundancy to be qualified for the space mission application domain. We conduct an experimental study to evaluate the performance analysis by using image recognition algorithms based on an open source intelligent machine library 'MIOpen' and an open standard 'OpenVX'. OpenVX is a cross-platform computer vision library.

Series
IEEE Aerospace Conference Proceedings, ISSN 1095-323X
Keywords
Heterogeneous System Architecture (HSA)Intelligent Data ProcessingMIOpenOpenVXCubeSatCPU-GPUEnergy consumption
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-38628 (URN)10.1109/AERO.2018.8396536 (DOI)2-s2.0-85049840022 (Scopus ID)
Conference
IEEE Aerospace Conference 2018 IEEEAC2018, 03 Mar 2018, Big Sky, United States
Projects
DPAC - Dependable Platforms for Autonomous systems and Control
Available from: 2018-03-06 Created: 2018-03-06 Last updated: 2018-09-18Bibliographically approved
Bucaioni, A., Addazi, L., Cicchetti, A., Ciccozzi, F., Eramo, R., Mubeen, S. & Nolin, M. (2018). MoVES: a Model-driven methodology for Vehicular Embedded Systems. IEEE Access, 6424-6445
Open this publication in new window or tab >>MoVES: a Model-driven methodology for Vehicular Embedded Systems
Show others...
2018 (English)In: IEEE Access, E-ISSN 2169-3536, p. 6424-6445Article in journal (Refereed) Published
Abstract [en]

This paper introduces a novel model-driven methodology for the software development of real-time distributed vehicular embedded systems on single- and multi-core platforms. The proposed methodology discloses the opportunity of improving the cost-efficiency of the development process by providing automated support to identify viable design solutions with respect to selected non-functional requirements. To this end, it leverages the interplay of modelling languages for the vehicular domain whose integration is achieved by a suite of model transformations. An instantiation of the methodology is discussed for timing requirements, which are among the most critical ones for vehicular systems. To support the design of temporally correct systems, a cooperation between EAST-ADL and the Rubus Component Model is opportunely built-up by means of model transformations, enabling timing-aware design and model-based timing analysis of the system. The applicability of the methodology is demonstrated as proof of concepts on industrial use cases performed in cooperation with our industrial partners.

National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-38626 (URN)10.1109/ACCESS.2018.2789400 (DOI)000427230900001 ()2-s2.0-85041228300 (Scopus ID)
Projects
SynthSoft - Synthesizing Predictable Software for Distributed Embedded SystemsPreView: Developing Predictable Vehicle Software on Multi-coreMOMENTUM: analysis of models towards compilation to predictable embedded real-time and safety-critical applications
Available from: 2018-03-06 Created: 2018-03-06 Last updated: 2018-11-05Bibliographically approved
Bucaioni, A., Mubeen, S., Ciccozzi, F., Cicchetti, A. & Sjödin, M. (2017). A Metamodel for the Rubus Component Model: Extensions for Timing and Model Transformation from EAST-ADL. IEEE Access, 9005-9020
Open this publication in new window or tab >>A Metamodel for the Rubus Component Model: Extensions for Timing and Model Transformation from EAST-ADL
Show others...
2017 (English)In: IEEE Access, E-ISSN 2169-3536, ISSN 2169-3536, p. 9005-9020Article in journal (Refereed) Published
Abstract [en]

According to the Model-Driven Engineering paradigm, one of the entry requirements when realising a seamless tool chain for the development of software is the definition of metamodels, to regulate the specification of models, and model transformations, for automating manipulations of models. In this context, we present a metamodel definition for the Rubus Component Model, an industrial solution used for the development of vehicular embedded systems. The metamodel includes the definition of structural elements as well as elements for describing timing information. In order to show how, using Model-Driven Engineering, the integration between different modelling levels can be automated, we present a model-to-model transformation between models conforming to EAST-ADL and models described by means of the Rubus Component Model. To validate our solution, we exploit a set of industrial automotive applications to show the applicability of both the Rubus Component Model metamodel and the model transformation.

National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-29564 (URN)10.1109/ACCESS.2016.2641218 (DOI)000404270600034 ()2-s2.0-85025171666 (Scopus ID)
Available from: 2015-11-18 Created: 2015-11-18 Last updated: 2019-06-26Bibliographically approved
Bucaioni, A., Mubeen, S., Nolin, M., Lundbäck, J., Gålnander, M. & Lundbäck, K.-L. (2017). Demonstrating Model- and Component-based Development of Vehicular Real-time Systems. In: Open Demo Session of Real-Time Systems located at Real Time Systems Symposium (RTSS) RTSS@Work'17: . Paper presented at Open Demo Session of Real-Time Systems located at Real Time Systems Symposium (RTSS) RTSS@Work'17, 05 Dec 2017, Paris, France.
Open this publication in new window or tab >>Demonstrating Model- and Component-based Development of Vehicular Real-time Systems
Show others...
2017 (English)In: Open Demo Session of Real-Time Systems located at Real Time Systems Symposium (RTSS) RTSS@Work'17, 2017Conference paper, Published paper (Refereed)
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-37486 (URN)
Conference
Open Demo Session of Real-Time Systems located at Real Time Systems Symposium (RTSS) RTSS@Work'17, 05 Dec 2017, Paris, France
Projects
PreView: Developing Predictable Vehicle Software on Multi-core
Available from: 2017-12-20 Created: 2017-12-20 Last updated: 2017-12-20Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-7586-0409

Search in DiVA

Show all publications