In this paper, we investigate an artificialintelligence (AI) driven approach to design error correction codes (ECC). Classic error-correction code design based upon coding-theoretic principles typically strives to optimize some performance-related code property such as minimum Hamming distance, decoding threshold, or subchannel reliability ordering. In contrast, AI-driven approaches, such as reinforcement learning (RL) and genetic algorithms, rely primarily on optimization methods to learn the parameters of an optimal code within a certain code family. We employ a constructor-evaluator framework, in which the code constructor can be realized by various AI algorithms and the code evaluator provides code performance metric measurements. The code constructor keeps improving the code construction to maximize code performance that is evaluated by the code evaluator. As examples, we focus on RL and genetic algorithms to construct linear block codes and polar codes. The results show that comparable code performance can be achieved with respect to the existing codes. It is noteworthy that our method can provide superior performances to classic constructions in certain cases (e.g., list decoding for polar codes). Code PerformanceCoding Theory Code Construction AI Techniques Fig. 1: Error correction code design logic improve its code performance. Equivalently, given a target error rate, we optimize code design to maximize the achievable code rate, i.e. to approach the channel capacity. A. Code design based on coding theoryClassical code construction design is built upon coding theory, in which code performance is analytically derived in terms of various types of code properties. To tune these properties is to control the code performance so that code design problems are translated into code property optimization problems.Hamming distance is an important code property for linear block codes of all lengths. For short codes, it is the dominant factor in performance, when maximum-likelihood (ML) decoding is feasible. For long codes, it is also important for performance in the high signal-to-noise ratio (SNR) regime. A linear block code can be defined by a generator matrix G or the corresponding parity check matrix H over finite fields. Directed by the knowledge of finite field algebra, the distance profile of linear block codes can be optimized, and in particular, the minimum distance. Examples include Hamming codes, Golay codes, Reed-Muller (RM) codes, quadratic residue (QR) codes, Bose-Chaudhuri-Hocquenghem (BCH) codes, Reed-Solomon (RS) codes, etc.Similar to the Hamming distance profile, free distance, another code property, is targeted for convolutional codes. Convolutional codes [2] are characterized by code rate and the memory order of the encoder. By increasing the memory order and selecting proper polynomials, larger free distance can be obtained at the expense of encoding and decoding

Metal sulfides have been considered as one of the most promising class of anode materials for lithium‐ion batteries. However, large volume change and low intrinsic electrical conductivity significantly restrict the performance. Herein, flexible electrode materials comprising ZnS nanotubes/carbon cloth are prepared by combined solvothermal and ion‐exchange sulfidation technique. The ZnS nanotube array/carbon cloth electrode is assessed for application in lithium‐ion batteries and remarkable improvement towards reversible capacity was observed. A notable capacity of 1053 mAh g−1 at 0.2 C and a maintained reversible capacity of 608 mAh g−1 after 100 cycles are observed, which are both comparable to similar materials in previously published reports. The ZnS nanotubes with small dimension and uniform dispersion grown directly on carbon cloth can effectively shorten the path of the lithium‐ions, facilitating the charge transfer of the electrode. The carbon cloth and the three‐dimensional (3D) structured carbon fiber exhibit a large surface area and can thus efficiently reduce the volume change during the discharge/charge cycles.

The performances of various blind timing phase estimators (TPE) for digital coherent receiver are analyzed. The equivalence among four TPE algorithms is analytically presented, showing that two TPE algorithms applying squaring pre-filters are in fact identical. Three TPE algorithms applicable to Nyquist signals are proposed based on the equivalence analysis. In addition, the impact of receiver bandwidths, spectrum weighting bandwidths and signal timing phases on TPE performance are investigated. The definition of sampling diversity and the analysis of sampling diversity gain for four pulse shapes are presented. The effect of sampling diversity is observed and verified via both simulations and experiments.

Mesoporous ZnO nanosheets are synthesized through a room temperature solvothermal method. Transmission and scanning electronic microscopy observations indicate that as-prepared ZnO hierarchical aggregates are composed and assembled by nanosheets with a length of 1–2 μm and a thickness of 10–20 nm, and interlaced ZnO nanosheets irregularly stack together, forming a three-dimensional network. Furthermore, large mesopores are embedded in the walls of ZnO nanosheets, confirmed by Brunauer-Emmett-Teller (BET) measurement. Accordingly, the resulting ZnO anode exhibits a high and stable specific discharge capacity of 421 mAh g−1 after 100 cycles at 200 mA g−1 and a good rate capability. Such electrochemical performance could be attributed to the multiple synergistic effects of its mesoporous nanosheet structure, which can not only provide a large specific surface area for lithium storage, but also favor the ion transport and electrolyte diffusion.

No abstract

In this study, ternary Cu2SnS3 (CTS) nanostructure materials with high crystallinity were successfully prepared via a facile solvothermal method, which was followed by high-temperature treatment. The morphology of the as-synthesized samples is uniform flower-like spheres, with these spheres consisting of hierarchical nanosheets and possessing network features. Sodium storage measurements demonstrate that the annealed CTS electrodes have high initial reversible capacity (447.7 mAh·g−1 at a current density of 100 mA·g−1), good capacity retention (200.6 mAh·g−1 after 50 cycles at a current density of 100 mA·g−1) and considerable rate capability because of their high crystallinity and unique morphology. Such good performances indicate that the high crystallinity CTS is a promising anode material for sodium ion batteries.

In this work, a facile strategy to synthesize oxygen and nitrogen co-doped porous carbon (ONPC) is reported by one-step pyrolysis of waste coffee grounds. As-prepared ONPC possesses highly rich micro/mesopores as well as abundant oxygen and nitrogen co-doping, which is applied to sulfur hosts as lithium/sulfur batteries’ appropriate cathodes. In battery testing, the sulfur/oxygen and nitrogen co-doped porous carbon (S/ONPC) composite materials reveal a high initial capacity of 1150 mAh·g−1 as well as a reversible capacity of 613 mAh·g−1 after the 100th cycle at 0.2 C. Furthermore, when current density increases to 1 C, a discharge capacity of 331 mAh·g−1 is still attainable. Due to the hierarchical porous framework and oxygen/nitrogen co-doping, the S/ONPC composite exhibits a high utilization of sulfur and good electrochemical performance via the immobilization of the polysulfides through strong chemical binding.

In this paper, we model nested polar code construction as a Markov decision process (MDP), and tackle it with advanced reinforcement learning (RL) techniques. First, an MDP environment with state, action, and reward is defined in the context of polar coding. Specifically, a state represents the construction of an (N, K) polar code, an action specifies its reduction to an (N, K − 1) subcode, and reward is the decoding performance. A neural network architecture consisting of both policy and value networks is proposed to generate actions based on the observed states, aiming at maximizing the overall rewards. A loss function is defined to trade off between exploitation and exploration. To further improve learning efficiency and quality, an "integrated learning" paradigm is proposed. It first employs a genetic algorithm to generate a population of (sub-)optimal polar codes for each (N, K), and then uses them as prior knowledge to refine the policy in RL. Such a paradigm is shown to accelerate the training process, and converge at better performances. Simulation results show that the proposed learning-based polar constructions achieve comparable, or even better, performances than the state of the art under successive cancellation list (SCL) decoders. Last but not least, this is achieved without exploiting any expert knowledge from polar coding theory in the learning algorithms.