Learning to Equalize: Data-Driven Frequency-Domain Signal Recovery in Molecular Communications

2025-09-14

AI Summary

To address reliability degradation caused by inter-symbol interference (ISI) and noise in molecular communication, this paper proposes a data-driven frequency-domain equalization (FDE) method. The approach uniquely integrates a Long Short-Term Memory (LSTM) network into the FDE framework, leveraging its capability to model temporal correlations in the channel impulse response for adaptive signal recovery—without requiring prior channel knowledge. Unlike conventional FDE methods that rely on accurate channel models or computationally intensive time-domain equalizers, the proposed scheme preserves the computational efficiency of frequency-domain processing while enabling effective temporal feature extraction and robust noise suppression. Experimental results under typical diffusion-based channels demonstrate that the method significantly reduces bit error rate compared to conventional FDE and feedforward neural network-based equalizers, achieves faster convergence, and incurs lower computational complexity.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In molecular communications (MC), inter-symbol interference (ISI) and noise are key factors that degrade communication reliability. Although time-domain equalization can effectively mitigate these effects, it often entails high computational complexity concerning the channel memory. In contrast, frequency-domain equalization (FDE) offers greater computational efficiency but typically requires prior knowledge of the channel model. To address this limitation, this letter proposes FDE techniques based on long short-term memory (LSTM) neural networks, enabling temporal correlation modeling in MC channels to improve ISI and noise suppression. To eliminate the reliance on prior channel information in conventional FDE methods, a supervised training strategy is employed for channel-adaptive equalization. Simulation results demonstrate that the proposed LSTM-FDE significantly reduces the bit error rate compared to traditional FDE and feedforward neural network-based equalizers. This performance gain is attributed to the LSTM's temporal modeling capabilities, which enhance noise suppression and accelerate model convergence, while maintaining comparable computational efficiency.

Problem

• Mitigate ISI and noise in molecular communications
• Reduce computational complexity of signal recovery
• Eliminate reliance on prior channel knowledge

Innovation

• LSTM neural networks for frequency-domain equalization
• Supervised training for channel-adaptive equalization
• Temporal correlation modeling for ISI suppression