Published papers

We propose applying a neural network-based demodulator and SD-FEC to b-modulation. We demonstrate that the transmission distance of a 64-QAM signal can be extended to 5,000 km using the proposed method through numerical simulations.

We propose the application of an SD-FEC technique to an eigenvalue-modulated signal using a multilabel neural-network demodulator. The experimental results indicate a successful operation with an error-free transmission through a 3000-km optical fiber line.

Underwater networks are expected to be service platforms for broad-sea and deep-sea activities. The significant challenge of underwater communication has been achieving high-speed and long-distance data transmission due to the high-attenuation and time-varying channel state in underwater environments. It is reasonable to get the underwater data above the water surface for establishing underwater-ground networks. However, it is still an unsolved issue to efficiently establish underwater-ground communication channel. To address this problem, we propose an aquatic fronthaul for underwater-ground communication, where floating aquatic relay nodes relay data from underwater drones/sensors to a ground radio unit. We propose a relocation algorithm for aquatic relay nodes to efficiently reconstruct the network according to the distribution of underwater nodes. The advantage of the proposed algorithm is robustness for the uncertainty of underwater node locations due to the difficulty in underwater localization. The performance of the proposed algorithm was evaluated with multi-agent simulations. The feasibility of the aquatic fronthaul network was confirmed via the experimental results with a Wi-Fi mesh network above the water.

Optical Camera Communication (OCC) is a promising solution for future wireless communication thanks to the advantages including security, license, and cost-efficiency. Widely available smart devices with em-bedded cameras such as smartphones, tablets, and digital cameras can be employed as receivers in OCC with-out modifying hardware. A complementary metal-oxide-semiconductor (CMOS) sensor in a camera can receive optical signals from multiple light sources at the same time. Since the light source occupies a certain area in the image plane, the received signal powers differ among the corresponding pixels. When the number of light sources increase, the signals from a light source can be blocked by another light source or affected by the blooming effect of other optical signals. However, there has never been a general model for avoiding such interference in OCC. Therefore, in this paper we propose a general model for avoiding inter-light sources interference. The proposed model formulates the constraints with perspective transformation based on the parameters of an image sensor and a camera. We also provide preliminary experimental results to validate the proposed model.

Optical eigenvalue transmission is a promising technique to overcome Kerr nonlinear limits in optical communication systems. The optical eigenvalue associated with the nonlinear Schrödinger equation is invariant during fiber-based nonlinear dispersive transmission. However, the effect of carrier frequency offset (CFO) induces an eigenvalue shift in the presence of the CFO for digitally coherent receivers. The CFO estimation method using eigenvalues capable of achieving highly accurate estimations and can be applied to an eigenvalue transmission system has been proposed. However, a detailed analysis of the eigenvalue-based CFO estimation method is yet to be examined. This study examines the estimation accuracy and limitations of the CFO estimation method through numerical simulations and experiments. The eigenvalue-based method achieves estimation accuracy of less than 10 kHz when the time window size bm W=6.4 ns and sampling rate bm R_s=20 GSa/s in numerical simulations. Moreover, the estimation error is proportional to energy loss when the time window size bm W and sampling rate bm R_s are limited. Through experiments, we achieve a fine estimation accuracy below 1 MHz when bm W=12.8 ns and bm R_s=5 GSa/s, although the accuracy is limited by the noise effect.

Deep joint source-channel coding (DeepJSCC) has emerged as a promising paradigm that integrates source and channel coding into an end-to-end learned transmission pipeline. While conventional DeepJSCC models are typically trained for a fixed compression rate, practical communication requires flexible adaptation to varying bandwidths and channel conditions. This work proposes a simple yet effective design of rateless DeepJSCC that applies stochastic masking along the channel dimension of the encoder's final convolutional layer. By assigning learned priorities to channels and transmitting only a subset according to available resources, the model achieves rateless adaptability while preserving the CNN-based property of being independent of input image resolution. Through experiments, we validate the effectiveness of the proposed approach. On CIFAR-10, the method achieves more stable training and slightly better PSNR and SSIM compared with the conventional rateless DeepJSCC, especially at low symbol-per-pixel (SPP) rates. On DIV2K, the proposed method achieves performance comparable to individually trained fixed-rate DeepJSCC models, while maintaining the advantage of size-independence. Overall, the results demonstrate that the proposed method provides stable and efficient rate adaptation.

We propose a multi-thread adaptive frequency-domain equalizer. The proposed scheme reduces the calculation cost by 87.5% with 128 taps and 1024 GPU threads while operating with the same performance as the multi-thread time domain equalizer.

Eigenvalue-based communication technologies using inverse scattering transform (IST) have gained attention as a new transmission strategy in optical fiber communications. In recent years, several studies on artificial neural network (ANN)-based equalization and demodulation schemes for eigenvalue-modulated signal have been conducted to enhance the receiver sensitivity. However, in the case of a presence of a carrier frequency offset (CFO) at receiver, the effects of the CFO on ANN receiver of eigenvalue-modulated signal is yet to be reported. In this study, we numerically and experimentally investigated the generalization performances of eigenvalue domain ANN-based demodulator on CFO. Furthermore, we propose to combine an ANN-based demodulator with a CFO compensation method based on IST and a relation between frequency and eigenvalue shifts. The proposed method, based on an appropriate soliton pulse, achieves a high CFO estimation accuracy of submegahertz order even if the CFO reaches $\pm$2.5 GHz under the noiseless condition. In the presence of noise and a large CFO of 2.5 GHz, the method attains a CFO estimation accuracy below 60 MHz for OSNR = 10 dB with a low pilot pulse rate, such as 0.064%. We show the simulation results obtained after applying the proposed CFO compensation to the ANN demodulator, which is valid for 2.5 GHz CFO and long-haul transmission over 5000 km. Experiments performed in this study demonstrate successful demodulation of an eigenvalue-modulated signal with OSNR penalty $< $ 1 dB in the presence of CFO within 1 GHz at 2.5 Gb/s.

Underwater communication is a promising technology to provide ubiquitous network connectivity, where acoustic waves are used as the primary carrier for long-range communication. It has been a challenging research topic to efficiently transmit images with under-water acoustic communication (UAC), due to its inherently narrow bandwidth, strong signal attenuation, time-varying multipath propagation, and low propagation speed. In this paper, we present a new approach to addressing these limitations in UAC, namely the joint source-channel coding and modulation (JSCCM) based on a deep neural network (DNN). We develop a training method of DNN-based encoder and decoder, which directly encode/decode image-pixel values to modulated symbols, unlike conventional separation-based source and channel coding and modulation. Through numerical simulations, the deep JSCCM is confirmed to achieve significantly higher data-rate than conventional schemes.