| 1. |
- Guimarães, Carlos, et al.
(författare)
-
DEEP : A Vertical-Oriented Intelligent and Automated Platform for the Edge and Fog
- 2021
-
Ingår i: IEEE Communications Magazine. - : IEEE. - 0163-6804 .- 1558-1896. ; 59:6, s. 66-72
-
Tidskriftsartikel (refereegranskat)abstract
- The fifth generation (5G) of mobile communications introduces improvements on many fronts when compared to its previous generations. Besides the performance enhancements and new advances in radio technologies, it also integrates other technological domains, such as cloud-to-things continuum and artificial intelligence. In this work, the 5G-DIVE Elastic Edge Platform (DEEP) is proposed as the linking piece for the integration of these technological domains, making available an intelligent edge and fog 5G end-to-end solution. This solution brings numerous benefits to vertical industries by enabling streamlined, abstracted, and automated management of their vertical services, thus contributing to the introduction of novel services, cost savings, and improved time to market. Preliminary validation of the proposed platform is performed through a proof of concept, along with a qualitative analysis of its benefits for Industry 4.0 and autonomous drone scouting vertical industries.
|
|
| 2. |
- Hazra, Saptarshi, et al.
(författare)
-
Battery-free Neighbor Discovery
- 2023
-
Ingår i: IPSN '23. - : Association for Computing Machinery (ACM). - 9798400701184 ; , s. 318-319
-
Konferensbidrag (refereegranskat)abstract
- Ensuring two battery-free devices discover each other to start communication is challenging due to intermittent and unpredictable energy availability. In this abstract, we exploit ultra-low power channel sensing to enable efficient neighbor discovery. Preliminary results show our method is promising in various ambient energy scenarios.
|
|
| 3. |
- Hazra, Saptarshi, et al.
(författare)
-
Demo : Multi-Radio Access Technology IoT Gateway
- 2020
-
Ingår i: Proceedings of the 2020 International Conference on Embedded Wireless Systems and Networks. - : Junction Publishing. ; , s. 189-191
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- We present VGATE, a softwarised, multiple-RAT IoT gateway. The baseband of IEEE 802.15.4, LoRa and NB-IoT are implemented with software-defined radio in containers that can execute in an edge computing platform. The demo shows simultaneous multi-channel access and simultaneous execution of multiple RATs in a shared infrastructure.
|
|
| 4. |
|
|
| 5. |
- Hazra, Saptarshi, et al.
(författare)
-
Handling inherent delays in virtual IoT gateways
- 2019
-
Ingår i: Proceedings - 15th Annual International Conference on Distributed Computing in Sensor Systems, DCOSS 2019. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728105703 - 9781728105710 ; , s. 58-65
-
Konferensbidrag (refereegranskat)abstract
- Massive deployment of diverse ultra-low power wireless devices in different application areas has given rise to a plethora of heterogeneous architectures and communication protocols. It is challenging to provide convergent access to these miscellaneous collections of communicating devices. In this paper, we propose VGATE, an edge-based virtualized IoT gateway for bringing these devices together in a single framework using SDRs as technology agnostic radioheads. SDR platforms, however, suffer from large unpredictable delays. We design a GNU Radio-based IEEE 802.15.4 experimental setup using LimeSDR, where the data path is time-stamped at various points of interest to get a comprehensive understanding of the characteristics of the delays. Our analysis shows that GNU Radio processing and LimeSDR buffering delays are the major delays. We decrease the LimeSDR buffering delay by decreasing the USB transfer size but show that this comes at the cost of increased processing overhead. We modify the USB transfer packet size to investigate which USB transfer size provides the best balance between buffering delay and processing overhead across two different host computers. Our experiments show that for the best measured configuration the mean and jitter of latency decreases by 37% and 40% respectively for the host computer with higher processing resources. We also show that the throughput is not affected by these modifications.
|
|
| 6. |
- Hazra, Saptarshi, et al.
(författare)
-
PLIO : Physical Layer Identification using One-shot Learning
- 2021
-
Ingår i: 2021 IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems (MASS). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781665449359 - 9781665449366 ; , s. 335-343
-
Konferensbidrag (refereegranskat)abstract
- The Internet of Things (IoT) is connecting a massive scale of everyday objects to the internet. We need to ensure the secure connectivity and authentication of these devices. Physical (PHY)-layer identification methods can distinguish between different devices by leveraging their unique hardware imperfections. But these methods typically require large quantities of training data which makes them impractical for large deployment scenarios. Also, these methods do not address the PHY-layer identification of new devices joining an IoT network. In this paper, we propose a PHY-layer identification method using one-shot learning that can identify new devices using the network solicitation packet of the devices as reference packets. We show that our method can accurately identify new devices without training, achieving a precision and recall over 80% even in the presence of 10 dBm noise. Furthermore, we show that with minimal retraining using only three packets from each device, we can accurately identify all devices in the IoT network with a precision and recall of 93%.
|
|
| 7. |
- Hazra, Saptarshi, et al.
(författare)
-
Shadow-based Hand Gesture Recognition in one Packet
- 2020
-
Ingår i: Proceedings - 16th Annual International Conference on Distributed Computing in Sensor Systems, DCOSS 2020. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728143514 ; , s. 27-34
-
Konferensbidrag (refereegranskat)abstract
- The ubiquity of wirelessly connected sensing devices in IoT applications provides the opportunity to enable various types of interaction with our digitally connected environment. Currently, low processing capabilities and high energy costs for communication limit the use of energy-constrained devices for this purpose. In this paper, we address this challenge by exploring the new possibilities highly capable deep neural network classifiers present. To reduce the energy consumption for transferring continuously sampled data, we propose to compress the sensed data and perform classification at the edge. We evaluate several compression methods in the context of a shadow-based hand gesture detection application, where the classification is performed using a convolutional neural network. We show that simple data reduction methods allow us to compress the sensed data into a single IEEE 802.15.4 packet while maintaining a classification accuracy of 93%. We further show the generality of our compression methods in an audio-based interaction scenario.
|
|
| 8. |
|
|
