Food perception is a multisensory experience shaped by environmental cues such as ambient lighting. Previous studies have demonstrated that lighting can impact how satisfied we feel while dining. However, many of these studies were conducted in controlled laboratory settings with standardized meals, overlooking how lighting interacts with personal dietary choices and diverse dining contexts. This paper introduces LumiBite, a portable lighting system integrated into a lunchbox, designed for dining environments to enable personalized lighting adjustments during meals. Through a seven-day in-the-wild study with six participants, where they freely chose when, what, and where to eat, we explored the feasibility of deploying LumiBite and investigated how user agency in customizing lighting settings impacts dining satisfaction, sensory perception and dietary behaviors. Our findings demonstrate that LumiBite not only enhances food aesthetics but also shifts users from passive consumers to active meal curators. The study highlights key challenges, including cultural dining practices and ambient light interference, and offers actionable design principles for creating context-aware, culturally sensitive dining technologies.

Designing robust and efficient codes for reliable communication in noisy environments is a key challenge. Recent advancements show that deep learning-based channel codes can outperform traditional handcrafted ones in certain scenarios. Despite recent advancements, most state-of-the-art codes are trained using the binary cross-entropy (BCE) loss, LBCE, which aims to optimize bit error rate (BER) but is less effective at minimizing block error rate (BLER) – a critical metric for avoiding costly re-transmissions in wireless systems. To address this limitation, we first apply several recently-proposed BLER-specific loss functions to train channel autoencoders, i.e., to design both the neural encoder and the matched neural decoder. Our results show that the application of such loss functions improves the design of autoencoders, compared to the conventional BCE loss, especially when BLER is the performance metric of interest. Next, we introduce a novel loss function, called the adaptively-scaled norm (ASN) loss, LASN, which dynamically adjusts penalties based on the error rates across the bit positions, making it more effective for BLER minimization. Compared to existing methods, the proposed loss function promotes a lower variance for the contribution from different bit positions while still emphasizing more on the bit positions with higher chances of error. Using a two-step process of pre-training and fine-tuning, we show that LASNoutperforms LBCEand the existing BLER-minimizing loss functions across various communication channels.

This paper presents a novel methodology for designing the reliability sequence π for polarization-adjusted convolutional (PAC) and polar codes. Given a sequence π of length N, a family of nested information sets is constructed for N codes. The design objective is to minimize the average of the minimum signal-to-noise ratios (SNRs) required to achieve a target block error rate (BLER) across these nested codes. To reduce the search space, the N bit positions are partitioned into M components of length N/M, with bit positions within each component following a predefined reliability order. The design problem is then formulated as a Markov decision process (MDP) and solved using a deep Q-network (DQN) with an experience replay buffer. Simulation results under CRC-aided successive cancellation list (CA-SCL) decoding for nested polar codes show that the proposed sequence improves SNR performance over existing nested polar codes, including those used in 5G. Additionally, nested PAC codes under successive cancellation list (SCL) decoding with the proposed π outperform nested PAC and polar codes based on the known reliability sequences, under SCL or CA-SCL decoding. Moreover, individual PAC codes extracted from the nested family perform competitively with the best-known PAC/polar codes designed for specific rates. The proposed method is applicable to various precoded polar code constructions and decoding algorithms. The observed performance improvements, particularly in PAC codes, suggest that this approach is a promising candidate for future communication systems, including 6G.

This paper introduces a novel rate-profile design for Polarization-Adjusted Convolutional (PAC) codes by simplifying the construction of an information set (inf set) for a PAC code of length$N$into the design of inf sets for$M$component codes of length$\frac{N}{M}$. We define a Markov Decision Process (MDP) that formulates the task of identifying the inf set that minimizes the Block Error Rate (BLER). To achieve this, we employ a Deep QNetwork (DQN) with an experience replay buffer to determine the optimal inf set with the lowest BLER. Simulation results demonstrate that under Successive Cancellation List (SCL) decoding, our designed PAC codes improve BLER compared to state-of-the-art PAC codes. This method is not limited to the design of PAC code inf set; it is applicable to inf set design for the general family of precoded Polar codes and supports any decoder.

We propose a channel auto-encoder which incorporates the encoding and decoding structure of classical generalized concatenated code (GCC) based on polar codes. The outer encoder and decoder of classical GCC polar codes are implemented by non-linear functions parameterized with a transformer based neural network. Our results show that the proposed scheme results in enhanced reliability of classical polar codes under SC decoding.

Turbo Autoencoder (TAE) is a deep-learning based channel code that demonstrates promising error correction performance. This paper studies the rate-matching problem for TAE and proposes a rate-matched TAE framework. The rate-matched TAE is a single auto-encoder model that can be used for multiple code rates. It matches the code rate of a mother$(3k, k)$TAE to a desired code of parameters ($n^{\ast}, k^{\ast}$) by using a combination of freezing message bits, repeating code symbols, and puncturing code symbols. We refer to the conventional TAE with message word length$k$and code length$3k$as mismatched TAE. The rate-matched TAE shares the same encoder and decoder structure with mismatched TAE but is trained to jointly optimize the performance across multiple rates. We study two important hyper-parameters for the rate-matched TAE: puncturing pattern and training signal-to-noise ratio (SNR) for constituent rates. Three puncturing patterns, namely, head, tail, and uniform puncturing are proposed and evaluated. Training SNRs are determined according to a heuristic method that uses test loss as a performance metric. Our simulation results show that the rate-matched TAE for$k= 100$and rates$r\in \{0.1, 0.2, \ldots, 0.9\}$significantly outperforms the mismatched TAE when$r\geq 0.4$.

This paper evaluates the performance of Turbo Autoencoder (TurboAE), an end-to-end jointly trained neural channel encoder and decoder, for different well-known inter-leavers over additive white Gaussian noise (AWGN) channel. TurboAE and Turbo codes share structural similarities. Therefore, in search of suitable interleavers for TurboAE, it is important to examine the interleavers designed for Turbo codes. In this paper, different interleavers are compared for TurboAE, and it is shown that using interleavers such as Quadratic Permutation Polynomial (QPP) and S-random interleavers provides considerable performance gain. The interleaver gain is achieved for both TurboAE made of convolutional neural network (CNN) layers and TurboAE made of recurrent neural networks (RNN) layers. Certain techniques are also proposed to enhance the performance of TurboAE RNN.

In this paper we investigate the problem of precoder selection assuming compressed channel state information (CSI) feedback over sub-bands. Typically (e.g., in NR Rel-16) the problem is approached by a two-step solution: independent precoder optimization for each sub-band, followed by selection of the compression bases. We show that such conventional approach does not perform well in scenarios of medium/high frequency selectivity. Then, we derive an alternative approach, based on wideband capacity maximization, which provides superior performance under frequency-selective channels, while being compatible with the existing NR Rel-16 framework without any additional signaling. We finally propose an adaptive method in which the receiver dynamically selects the wideband or the sub-band optimization strategy, depending on the instantaneous channel condition. The proposed approach achieves consistent gains (up to 3dB) in all the considered test cases.

In this paper, we present list autoencoder (listAE) to mimic list decoding used in classical coding theory. With listAE, the decoder network outputs a list of decoded message word candidates. To train the listAE, a genie is assumed to be available at the output of the decoder. A specific loss function is proposed to optimize the performance of a genie-aided (GA) list decoding. The listAE is a general framework and can be used with any AE architecture. We propose a specific architecture, referred to as incremental-redundancy AE (IR-AE), which decodes the received word on a sequence of component codes with non-increasing rates. Then, the listAE is trained and evaluated with both IR-AE and Turbo-AE. Finally, we employ cyclic redundancy check (CRC) codes to replace the genie at the decoder output and obtain a CRC aided (CA) list decoder. Our simulation results show that the IR-AE under CA list decoding demonstrates meaningful coding gain over Turbo-AE and polar code at low block error rates range.

There have been significant research activities in recent years to automate the design of channel encoders and decoders via deep learning. Due the dimensionality challenge in channel coding, it is prohibitively complex to design and train relatively large neural channel codes via deep learning techniques. Consequently, most of the results in the literature are limited to relatively short codes having less than 100 information bits. In this paper, we construct ProductAEs, a computationally efficient family of deep-learning driven (encoder, decoder) pairs, that aim at enabling the training of relatively large channel codes (both encoders and decoders) with a manageable training complexity. We build upon the ideas from classical product codes, and propose constructing large neural codes using smaller code components. More specifically, instead of directly training the encoder and decoder for a large neural code of dimension k and blocklength n, we provide a framework that requires training neural encoders and decoders for the code parameters (n1,k1) and (n2,k2) such that n1n2= n and k1k2= k. Our training results show significant gains, over all ranges of signal-to-noise ratio (SNR), for a code of parameters (225,100) and a moderate-length code of parameters (441,196), over polar codes under successive cancellation (SC) decoder. Moreover, our results demonstrate meaningful gains over Turbo Autoencoder (TurboAE) and state-of-the-art classical codes. This is the first work to design product autoencoders and a pioneering work on training large channel codes.

This paper enhances the performance and training of the Turbo Autoencoder (TurboAE), an end-to-end jointly trained neural channel encoder and decoder. A novel interleaver for TurboAE with convolutional neural network (CNN) is proposed, which is shown to enhance the end-to-end performance of both TurboAE continuous and binary. Thanks to the proposed interleaver, TurboAE binary performs better than a benchmark Turbo code of length 100. In addition, a novel additional term to the loss function is proposed to improve the pairwise distance distribution of the codewords, which is shown to help the training convergence of TurboAE with CNN and recurrent neural network (RNN).

The throughput of successive cancellation decoding of polar codes can be improved through simplified decoders that identify specific constituent codes in the decoding tree. The identified codes include rate-0, rate-1, repetition, and single parity-check codes. In this work, constituent codes that belong to the family of first-order Reed-Muller codes, and their sub-codes, are also identified in the decoding tree. Alternative decoding schemes that utilize the structure of Reed-Muller codes are incorporated into successive cancellation decoding. Simulation results show that such an approach can improve both the block error rate performance as well as the decoding latency of polar codes.

Deep learning has shown an unprecedented success in many fields such as computer vision and speech recognition, providing solutions to intractable problems. Deep learning has also provided solutions to several intractable problems in communications systems. This paper uses a deep learning approach to optimize the analytically intractable offset value in the offset-min-sum (OMS) algorithm. OMS algorithm is a very attractive low complexity algorithm that is used in the belief propagation decoding of linear codes. The contributions of this paper are: First, providing a low complexity offset optimization framework based on gradient descent and back propagation on the original Tanner graph. Our proposed algorithm has comparable complexity and similar operation as the forward belief propagation decoding algorithm and hence, can be trained much more efficiently. Second, the framework can be easily extended to any decoding scheduling such as flooding or layered scheduling. Training results show that the proposed framework can find the optimal offset value under different decoding scheduling with the same complexity of the belief propagation algorithm.

In this paper, we propose a novel method of reducing the complexity of a pilot-based two-dimensional linear minimum mean square error (2D LMMSE) channel estimation scheme for orthogonal frequency division multiplexing (OFDM) systems. We identify that the 2D LMMSE channel estimation method aided by pilots embedded in a two-dimensional OFDM resource grid can be decoupled into three steps: (a) pilot denoising, (b) interpolation in each of OFDM symbols including pilots, and (c) interpolation across OFDM symbols. In the denoising step, we process pilots only for noise reduction. In the following interpolation steps, we utilize two-dimensional channel correlation across subcarriers (frequency) and across OFDM symbols (time) in order to get channel estimates of interest. Under the assumption that the frequency and time correlations are disjoint and the channel correlation can be represented by the product of them, we show that the channel interpolation can be performed in two steps along the frequency domain first and then along the time domain. By taking advantage of this separation, we can reduce the complexity of 2D LMMSE considerably while still achieving the optimal performance of it.

To deal with a time-varying nature of the wireless channel, the most modern wireless systems use link adaptation in which the transmission rate is adjusted according to the current fading status to ensure reliable communication. For example, the current long-term evolution (LTE) standards require the user equipment (UE) to report channel quality indicator (CQI) to the base station (BS) to determine the data rate of a transmission (code) block. Such link adaptation effectively eliminates fading-induced outage and provides ergodic throughput in the long run. When there is delay in CQI feedback, however, such knowledge of the channel status is inevitably outdated, and outage becomes problematic again. In this paper, we characterize a future channel in which the reported CQI is actually used as a conditional random variable given current channel observation. The dependence of the future channel to the current observation is captured by channel correlation. By considering an outage event as a failed transmission, we can compute probability of successful transmission for each value of transmission rate to determine the best transmission rate which maximizes the expected throughput. If ergodicity holds for a channel process, then such expected throughput becomes close to an empirical throughput in the long run.

The paper establishes the optimal generalized degrees of freedom (GDOF) of 3-user M × N multiple-input multiple-output (MIMO) Gaussian interference channel (GIC) in which each transmitter has M antennas and each receiver has N antennas. A constraint of 2M ≤ N is imposed so that random coding with message-splitting achieves the optimal GDOF. Unlike symmetric case, two cross channels to unintended receivers from each transmitter can have different strengths, and hence, well known Han-Kobayashi common-private message splitting would not achieve the optimal GDOF. Instead, splitting each user's message into three parts is shown to achieve the optimal GDOF as well as O(1) capacity approximation.

This paper discusses evaluation of the capacity region for interference networks with point-to-point (p2p) codes. Such capacity region has recently been characterized as union of several sub-regions each of which has distinctive operational characteristics. Detailed evaluation of this region, therefore, can be accomplished in a very simple manner by acknowledging such characteristics, which, in turn, provides an insight for a simple implementation scenario. Generalized message assignment is considered in this paper, and it is shown to provide strictly larger achievable rates than what traditional message assignment does when a receiver with joint decoding capability is used.

Third Generation Partnership Project Long Term Evolution (3GPP LTE) provides potential of higher spectral efficiency by using multi-user multiple-input and multiple-output (MU-MIMO) system. Because of the coarse knowledge of channel state information at the transmitter (CSIT) under current standard, co-scheduled user equipments (UEs) may suffer large residual multi-user interference in MU-MIMO. In this paper, we investigate performances of various types of receivers in the cases where residual interference is not negligible. Interference ignoring receiver is expected to perform poorly in this scenario, and hence, we consider interference-aware receivers. Interference rejection combiner (IRC) and joint Max-Log-MAP receiver are considered as interference-aware receivers. In order to perform joint detection of the target and interference layers, UE needs to know interference modulation which current standard does not provide. Because of this, we consider modulation-estimation-based joint receiver as our advanced downlink MU-MIMO receiver. Performances of aforementioned receivers are investigated in several practically relevant cases. It is shown that modulation-estimation-based joint receiver can significantly outperform IRC or the joint receiver with assumption of fixed interference modulation.

In this paper, we investigate performances of simple transmission strategies. We first consider two user SISO Gaussian symmetric interference channel (IC) for which Etkin, Tse and Wang proposed a scheme (ETW scheme) which achieves one bit gap to the capacity. We compare performance of point-to-point (p2p) codes with that of the ETW scheme in practical range of transmitter power. It turns out that p2p coding scheme performs better or as nearly good as the ETW scheme. Next, we consider K user SISO Gaussian symmetric IC. We define interference regimes for K user SISO Gaussian symmetric IC and provide closed-form characterization of the symmetric rate achieved by the p2p scheme and the ETW scheme. Using this characterization, we evaluate performances of simple strategies with K=3, and show the similar trend to two user case.

For a memoryless channel, although feedback cannot increase capacity, it can reduce the complexity and/or improve the error performance of a communication system. Recently, Shayevitz and Feder proposed the posterior matching scheme (PMS) which is a simple recursive transmission scheme that achieves the capacity of memoryless channels with feedback. Furthermore, Coleman provided a Lyapunov function approach to prove capacity achievability of the PMS. In this paper, we investigate a capacity-achieving PMS for the case of finite-state channels (FSCs). We first derive a single-letter expression for the capacity of the FSC with delayed output and state feedback by formulating the problem in a stochastic control framework. The resulting capacity expression can be evaluated using dynamic programming. We then propose a simple recursive PMS-like transmission scheme. To prove capacity achievability of the proposed PMS, we identify an appropriate Markov chain induced by the PMS.

Codes on sparse graphs have been shown to achieve remarkable performance in point-to-point channels with low decoding complexity. Most of the results in this area are based on experimental evidence and/or approximate analysis. The question of whether codes on sparse graphs can achieve the capacity of noisy channels with iterative decoding is still open, and has only been conclusively and positively answered for the binary erasure channel. On the other hand, codes on sparse graphs have been proven to achieve the capacity of memoryless, binary-input, output-symmetric channels with finite graphical complexity per information bit when maximum likelihood (ML) decoding is performed. In this paper, we consider transmission over finite-state channels (FSCs). We derive upper bounds on the average error probability of code ensembles with ML decoding. Based on these bounds we show that codes on sparse graphs can achieve the symmetric information rate (SIR) of FSCs, which is the maximum achievable rate with independently and uniformly distributed input sequences. In order to achieve rates beyond the SIR, we consider a simple quantization scheme that when applied to ensembles of codes on sparse graphs induces a Markov distribution on the transmitted sequence. By deriving average error probability bounds for these quantized code ensembles, we prove that they can achieve the information rates corresponding to the induced Markov distribution, and thus approach the FSC capacity.

Codes on sparse graphs have been shown to achieve remarkable performance in point-to-point channels with low decoding complexity. Most of the results in this area are based on experimental evidence and/or approximate analysis. The question of whether codes on sparse graphs can achieve the capacity of noisy channels with iterative decoding is still open, and has only been conclusively and positively answered for the binary erasure channel. On the other hand, codes on sparse graphs have been proven to achieve the capacity of memoryless, binary-input, output-symmetric channels with finite graphical complexity per information bit when maximum likelihood (ML) decoding is performed. In this paper, we consider transmission over finite-state channels (FSCs). We derive upper bounds on the average error probability of code ensembles with ML decoding. Based on these bounds we show that codes on sparse graphs can achieve the symmetric information rate (SIR) of FSCs, which is the maximum achievable rate with independently and uniformly distributed input sequences. In order to achieve rates beyond the SIR, we consider a simple quantization scheme that when applied to ensembles of codes on sparse graphs induces a Markov distribution on the transmitted sequence. By deriving average error probability bounds for these quantized code ensembles, we prove that they can achieve the information rates corresponding to the induced Markov distribution, and thus approach the FSC capacity.