In subsurface imaging, learning the mapping from velocity maps to seismic waveforms (forward problem) and waveforms to velocity (inverse problem) is important for several applications. While traditional techniques for solving forward and inverse problems are computationally prohibitive, there is a growing interest to leverage recent advances in deep learning to learn the mapping between velocity maps and seismic waveform images directly from data. Despite the variety of architectures explored in previous works, several open questions still remain unanswered such as the effect of latent space sizes, the importance of manifold learning, the complexity of translation models, and the value of jointly solving forward and inverse problems. We propose a unified framework to systematically characterize prior research in this area termed the Generalized Forward-Inverse (GFI) framework, building on the assumption of manifolds and latent space translations. We show that GFI encompasses previous works in deep learning for subsurface imaging, which can be viewed as specific instantiations of GFI. We also propose two new model architectures within the framework of GFI: Latent U-Net and Invertible X-Net, leveraging the power of U-Nets for domain translation and the ability of IU-Nets to simultaneously learn forward and inverse translations, respectively. We show that our proposed models achieve state-of-the-art (SOTA) performance for forward and inverse problems on a wide range of synthetic datasets, and also investigate their zero-shot effectiveness on two real-world-like datasets. The code is available at https://github.com/KGML-lab/Generalized-Forward-Inverse-Framework-for-DL4SI

Multiple unmanned aerial vehicle (UAV) aided communication is an invaluable innovation aiding in enhancing the quality of service by improving throughput and base station (BS) coverage, along with fostering line-of-sight (LOS) links, making it a potential asset in the sixth generation (6G) cellular communication networks. In this paper, we propose a full-duplex (FD) multi-UAV, non-orthogonal multiple access (NOMA)-aided UAV-to-UAV (U2U) communication system, wherein a selected UAV transmitter (UT) acts as a relay for the downlink cellular communications system along with participating in U2U communication. UT Selection is performed on the basis of signal-to-interference-plus-noise ratio (SINR) at the cellular user (CU). The selected UT employs NOMA to transmit the superimposed signal to the CU and UAV receiver (UR). A time-splitting (TS) energy harvesting (EH) scheme is designed to mitigate the low-power constraints of UAVs, and a novel UAV power-sharing scheme is described to improve energy efficiency. The Fluctuating Two-Ray (FTR) fading model has been utilized for the channel between any two nodes, and the self-interference (SI) link has been modeled using Rayleigh Fading. End-to-end outage probability analysis has been performed for both the cellular and U2U links and the impact of the EH parameters and the randomized FTR channel parameters on the outage probability has been described through Monte-Carlo simulations, which are further corroborated with theoretical analysis of outage probability.

This paper attempts to design a receiver for a single sideband (SSB) frequency shift keying (FSK) continuous phase modulation (CPM) scheme in a slow-fading Rayleigh channel for the 6 G communication system. The SSB-FSK, a new class of CPM introduced recently, which generates the SSB signal directly by using a Lorentzian shape pulse derived from quantum physics. In this work, we explore the utilization of SSB-FSK for low-power communication systems under the Rayleigh fading scenario, which has yet to be explored so far. We have proposed an SSB-FSK receiver with zero-forcing/minimum mean square error equalizer serially concatenated with the maximum a-posteriori (MAP) detector. Next, an analytical expression of the probability of bit error rate (BER) (Pb) for the proposed detector is derived in a slow Rayleigh fading channel. A thorough simulation study was performed, and it was obtained that the SSB-FSK gives nearoptimal BER performance to the MAP detector in the presence of a practical Rayleigh fading scenario.

Unmanned Aerial Vehicles (UAVs) are used for various applications such as surveillance, data collection, and military operations. Their adaptability in serving as aerial base stations bridge connectivity gaps, ensuring seamless communication in challenging environments. This paper proposes a non-orthogonal multiple access (NOMA) assisted full-duplex (FD) cooperative UAV-to-UAV (U2U) communications system wherein the UAV transmitter acts as an FD relay for cellular downlink signal. In addition, the UAVs employ an energy harvesting framework consisting of simultaneous wireless information and power transfer (SWIPT) and wireless power transfer (WPT) protocols to improve energy efficiency. The links between the communicating nodes are modeled by the fluctuating two-ray (FTR) fading, and a probabilistic mathematical model is developed for end-to-end cellular and U2U links. The impact of transmit-SNR, NOMA power allocation factor, and power splitting factor on the outage performance of the cellular and U2U links are analyzed.

The explosive growth of wireless data and traffic, accompanied by the rapid advancements in intelligence and processing power of user equipments (UEs), has paved the way for device-to-device (D2D) communication technology to surface as a promising solution. One major benefit is that users can collaboratively cache and share content to reduce costs associated with backhaul links. In this paper, we explore different approaches to cache content for users in a D2D enabled environment and propose a novel two-stacked approach to achieve a higher cache-hit ratio while leveraging advancements in deep learning. We propose the ‘R2-D2D’ framework, wherein we use Long Short-Term Memory (LSTM) networks stacked with a recently developed omni-scale convolutional neural network (CNN) for making the caching decision. Unlike most previous works, the proposed system model works without any apriori knowledge like file popularity distribution, or any assumptions like stationarity of the environment. Our experiments show that the proposed framework learns well from historical information, obtaining an overall average D2D cache hit ratio of 0.418 when 5000 timesteps of historical information were provided, outperforming a recently proposed neural network collaborative filtering (NCF) framework by approximately 10% to 25%.

This paper proposes orthogonal frequency division multiple access (OFDMA) based multiuser hybrid cooperative- D2D (C-D2D) communication system with the best user selection. In the proposed model, the listen-before-talk (LBT) algorithm with an energy detection method has been used to check the WiFi spectrum availability. Based on the spectrum availability, the system adapts to any one of the two modes, namely in-band C- D2D or out-band C-D2D. Further, the best user selection scheme is applied to a system wherein multiple D2D users coexist with a cellular user in the same cell. In particular, among the M available D2D pairs, selected D2D user helps the cellular user by relaying D out of N subcarriers to the base station (BS). Based on the availability of Wi-Fi, either N-D subcarriers of the cellular spectrum or N subcarriers of the Wi-Fi spectrum will be shared among M D2D users for D2D transmission. Closedform expressions of outage probability for cellular and D2D users are derived. Results show that the proposed hybrid C-D2D communication system with the best user selection outperforms the conventional C-D2D framework.

In the response phase of disaster management, immediate actions are taken by various organizations to fulfill humanitarian needs. In a post-disaster scenario, the aim of disaster relief team is to serve maximum people within a time constraint, but by increasing the cost of supply by a small amount if lives of more people can be saved, then increase in cost can be taken positively. This paper presents a web-based tool, which finds the relief vehicle routes among real locations and visualizes it on the map in a hassle-free way. In addition, to tackle the disaster scenario, two algorithms are proposed, namely priority-based route find (PBRF) and hybrid route find (HRF), for the post-disaster relief supply. PBRF is location priority-based algorithm, which is efficient in terms of serving the maximum number of people in a single trip, but it takes a longer time. HRF is a hybrid algorithm of PBRF and distance-based route find (DBRF), i.e., a traditional algorithm of solving the travelling salesman problem (TSP). Through various simulations, all three algorithms are compared in terms of time and number of people served. Results show that HRF is efficient compared to PBRF and DBRF.

Device-to-Device (D2D) communication, an influential addition to long term evolution- advanced (LTE-A) standards, enables direct communication between closely located cellular users to improve the throughput, latency and spectral efficiency of a cellular network. In this paper, we augment the development of D2D by proposing an orthogonal frequency division multiple access (OFDMA) based cooperative D2D (C-D2D) framework wherein multiple D2D pairs exist with a cellular user. Among M available D2D pairs, a D2D transmitter (DT) that can achieve the largest quality-of-service (QoS) improvement of uplink cellular transmission is selected to serve as a user relay for the cellular transmission. In addition, a novel round robin process with priority cube method is proposed to facilitate the fair distribution of available resources among M DTs. A generic mathematical probability model is developed to analyze the performance of the proposed scheme. In particular, the closed-form expression of the outage probability for the best D2D user selection for C-D2D framework is derived. Results show that the proposed scheme improves the QoS of the cellular user as compared to the conventional C-D2D framework.

Cooperative device to device (C-D2D) communication framework can be exploited for offloading cellular data as well as to combat congestion in a crowded cellular network. In C-D2D, a D2D transmitter (DT) acts as an in-band relay to satisfy the quality of service (QoS) requirements of a cellular user (CU). In this paper, we present the measurement results for orthogonal frequency division multiple access (OFDMA) based adaptive C-D2D communication framework. The measurements are conducted on a software re-configurable National Instruments (NI) Universal Software Radio Peripheral (USRP) platform. The on-field trials are carried out for both line of sight (LOS) and non-line of sight (N-LOS) measurement scenarios. Further, an adaptive subcarrier sharing scheme is also proposed to facilitate in-band D2D communication within a cellular network. The measurement results show that the adaptive and C-D2D framework significantly improves the bit error rate (BER) and spectral efficiency (SE) performance of the cellular network.

Device-to-Device (D2D) communication, an influential addition to long term evolution-advanced (LTE-A) standards enables direct communication between the closely located cellular users to improve the throughput, latency, and spectral efficiency of a cellular network. In this paper, we augment the development of D2D by proposing the orthogonal frequency division multiple access (OFDMA) based underlay and overlay D2D frameworks wherein multiple D2D users coexist with the cellular users in the same cell. A general mathematical probability model is developed to analyze the performance of both frameworks. Specifically, closed form expression to find minimum angle θ (an angle between the cellular link and D2D interference link) is derived for which the target rate and outage probability constraint of both cellular and D2D users are satisfied. By deducing the value of θ, BS can select an optimal cellular user to facilitate D2D communication in a cellular network.

A crisis is a terrible thing to waste. Quotes like this are often heard by experts in the industry and academia but what does this mean to me? How should I change my professional interests? How should I evolve my career? How is EDA going to evolve? The panel represents multiple points of views on these questions. Four experts will review the current job situation in EDA and provide a historical perspective for previous recessions. The panel will further discuss views on new directions for the Electronics market, how EDA should evolve, and options for career development during the slow down of the industry.