M. Yousof Naderi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
M. Yousof Naderi has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Kaushik Chowdhury
The University of Texas at Austin
3 shared publications - Carlos Bocanegra
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
2 shared publications - Sara Garcia Sanchez
IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
2 shared publications - Stratis Ioannidis
Northeastern University, Boston, MA, USA
2 shared publications - Ufuk Muncuk
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
2 shared publications - Yanzhi Wang
Northeastern University
2 shared publications
Latest Publications
- 14 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 31 (6) , 2470-2482
AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces
Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind convolution that uses over-the-air computation and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call ’AirNN’. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating convolutions with over-the-air computation. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.
- 14 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 31 (6) , 2470-2482
AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces
Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind convolution that uses over-the-air computation and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call ’AirNN’. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating convolutions with over-the-air computation. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.
- Open Access
AirNN: Neural Networks with Over-the-Air Convolution via Reconfigurable Intelligent Surfaces
Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind over-the-air convolution and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call 'AirNN'. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating over-the-air convolutions. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.
Open AccessAirNN: Neural Networks with Over-the-Air Convolution via Reconfigurable Intelligent Surfaces
Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind over-the-air convolution and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call 'AirNN'. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating over-the-air convolutions. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.
- 2 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 29 (3) , 1362-1375
WiFED Mobile: WiFi Friendly Energy Delivery With Mobile Distributed Beamforming
Wireless RF energy transfer for indoor sensors is an emerging paradigm ensuring continuous operation without battery limitations. However, high power radiation within ISM band interferes with packet reception for existing WiFi devices. The paper proposes the first effort in merging RF energy transfer within a standards compliant 802.11 protocol, realizing practical and WiFi-friendly Energy Delivery with Mobile Transmitters (WiFED Mobile). WiFED Mobile architecture is composed of a centralized controller coordinating the actions of multiple energy transmitters (ETs), and deployed sensors that periodically requires charging. The paper first describes 802.11 supported protocol features that can be exploited by sensors to request energy and for ETs to participate in energy transfer. Second, it devises a controller-driven bipartite matching algorithm, assigning appropriate number of ETs to sensors for efficient energy delivery. Thirdly, it detects outlier sensors (OS), which have limited power reception from static ETs and utilizes mobile ETs (METs) to satisfy their charging cycles. The proposed in-band and protocol supported coexistence in WiFED Mobile is validated via simulations and partly in a software defined radio testbed, showing that METs reduce latency by 42% and improve throughput by 83% in scenarios where using only static ETs fails to satisfy charging cycles of OS.
- 2 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 29 (3) , 1362-1375
WiFED Mobile: WiFi Friendly Energy Delivery With Mobile Distributed Beamforming
Wireless RF energy transfer for indoor sensors is an emerging paradigm ensuring continuous operation without battery limitations. However, high power radiation within ISM band interferes with packet reception for existing WiFi devices. The paper proposes the first effort in merging RF energy transfer within a standards compliant 802.11 protocol, realizing practical and WiFi-friendly Energy Delivery with Mobile Transmitters (WiFED Mobile). WiFED Mobile architecture is composed of a centralized controller coordinating the actions of multiple energy transmitters (ETs), and deployed sensors that periodically requires charging. The paper first describes 802.11 supported protocol features that can be exploited by sensors to request energy and for ETs to participate in energy transfer. Second, it devises a controller-driven bipartite matching algorithm, assigning appropriate number of ETs to sensors for efficient energy delivery. Thirdly, it detects outlier sensors (OS), which have limited power reception from static ETs and utilizes mobile ETs (METs) to satisfy their charging cycles. The proposed in-band and protocol supported coexistence in WiFED Mobile is validated via simulations and partly in a software defined radio testbed, showing that METs reduce latency by 42% and improve throughput by 83% in scenarios where using only static ETs fails to satisfy charging cycles of OS.
- 19 September 2019
- Published by Springer Nature
- p. 505-541
Next-Generation Software-Defined Wireless Charging System
- 19 September 2019
- Published by Springer Nature
- p. 505-541
Next-Generation Software-Defined Wireless Charging System
- Open Access
- 21 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 20 (12) , 2554-2557
On the Scalability of Energy in Wireless RF Powered Internet of Things
Wireless RF power transfer requires the deployment of multiple energy transmitters (ETs) to cover an entire area of interest. This letter aims at bounding the minimum cumulative power that ETs need to inject into the network, such that the recipient nodes harvest sufficient power to operate. The main findings are that, in the worst case, this scales as O(s 1-α/2 ), where s and α are the number of ETs and the channel path loss. That is, the overall power decreases with the number of ETs. It is also shown that sophisticated design for power transmission can further improve the scalability by s -1 .
- 21 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 20 (12) , 2554-2557
Open AccessOn the Scalability of Energy in Wireless RF Powered Internet of Things
Wireless RF power transfer requires the deployment of multiple energy transmitters (ETs) to cover an entire area of interest. This letter aims at bounding the minimum cumulative power that ETs need to inject into the network, such that the recipient nodes harvest sufficient power to operate. The main findings are that, in the worst case, this scales as O(s 1-α/2 ), where s and α are the number of ETs and the channel path loss. That is, the overall power decreases with the number of ETs. It is also shown that sophisticated design for power transmission can further improve the scalability by s -1 .
- 2 August 2007
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 43 (16) , 892-893
RWA problem for designing DWDM networks – delay against capacity optimisation
Adaptation of QoS in DWDM optical networks routing and the wavelength assignment (RWA) problem, known as an NP-hard problem, are addressed. The QoS constraint based routing RWA computes lightpaths for the original-destination node pair, (O, D), to meet the QoS propagation delay requirements. A heuristic algorithm based on a genetic algorithm (GA) is then developed to solve this problem. A simulation program is developed to demonstrate the efficiency of the GA for the COST 239 network. The trade-off between the capacity and the propagation delay has been analysed. Results show that the trade-off is 8.7% of the average capacity, increasing to 10.6% decrease for the average delay.
- 2 August 2007
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 43 (16) , 892-893
RWA problem for designing DWDM networks – delay against capacity optimisation
Adaptation of QoS in DWDM optical networks routing and the wavelength assignment (RWA) problem, known as an NP-hard problem, are addressed. The QoS constraint based routing RWA computes lightpaths for the original-destination node pair, (O, D), to meet the QoS propagation delay requirements. A heuristic algorithm based on a genetic algorithm (GA) is then developed to solve this problem. A simulation program is developed to demonstrate the efficiency of the GA for the COST 239 network. The trade-off between the capacity and the propagation delay has been analysed. Results show that the trade-off is 8.7% of the average capacity, increasing to 10.6% decrease for the average delay.