Decoding Method Research Articles

Construction of Polar Codes Based on Memetic Algorithm

As an emerging coding technique chosen by the 5th generation wireless systems (5G) standardization process, polar coding has attracted the attention of both academia and industry in recent years. The currently used construction methods of polar code are generally based on the reliability of each polarized sub-channel, which directly correspond to the Successive Cancellation (SC) decoding algorithm. However, much less is known about the optimal construction of polar codes under more sophisticated decoding methods such as the Successive Cancellation List (SCL) decoding. There is currently no perfect theory to derive the optimal construction for the SCL decoding to the best of our knowledge, because finding such optimal construction of SCL is considered to be a hard problem for normal choices of the list size. To address this problem, in this paper we turn to evolutionary computation, and propose a memetic algorithm by incorporating prior knowledge obtained from both the channel estimation of the SC-profile and the codeword weight evaluation of the RM-profile, shorted as MA-SCRM. The potential constructions of polar codes are expressed as binary sequences which are processed as the individuals of the population in MA-SCRM. Based on the prior knowledge obtained from the SC-profile and the Reed-Muller-profile, we design special initialization and evolutional operators for polar codes construction. An elitism archive is also introduced to maintain promising constructions and accelerate the convergence of the algorithm. For the SCL decoding, MA-SCRM obtains polar-coding constructions that are more excellent than the SC decoder construction in the sense of block error probability. Compared with the SC decoding construction method, MA-SCRM can reduce the block error probability by up to 48.78% for the original block error rate around <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$10^{-2}$</tex-math></inline-formula> , and more improvement can be observed for lower original block error rate.

Hippocampal activity predicts contextual misattribution of false memories

Failure of contextual retrieval can lead to false recall, wherein people retrieve an item or experience that occurred in a different context or did not occur at all. Whereas the hippocampus is thought to play a crucial role in memory retrieval, we lack understanding of how the hippocampus supports retrieval of items related to a target context while disregarding related but irrelevant information. Using direct electrical recordings from the human hippocampus, we investigate the neural process underlying contextual misattribution of false memories. In two large datasets, we characterize key physiological differences between correct and false recalls that emerge immediately prior to vocalization. By differentiating between false recalls that share high or low contextual similarity with the target context, we show that low-frequency activity (6 to 18 Hz) in the hippocampus tracks similarity between the current and retrieved context. Applying multivariate decoding methods, we were able to reliably predict the contextual source of the to-be-recalled item. Our findings elucidate one of the hallmark features of episodic memory: our ability to distinguish between memories that were formed on different occasions.

Extended Depth-of-Field Imaging Using Multi-Scale Convolutional Neural Network Wavefront Coding

Wavefront encoding (WFC) is a depth-of-field (DOF) extension technology that combines optical encoding and digital decoding. The system extends DOF at the expense of intermediate image quality and then decodes it through an image restoration algorithm to obtain a clear image. Affected by point spread differences, traditional decoding methods are often accompanied by artifacts and noise amplification problems. In this paper, based on lens-combined modulated wavefront coding (LM-WFC), we simulate the imaging process under different object distances, generate a simulation data set of WFC, and train a multi-scale convolutional neural network. The simulation experiment proves that this method can effectively reduce artifacts and improve image clarity. In addition, we used the LM-WFC camera to obtain real scene images with different target distances for experiments. The decoding results showed that the network model can enhance the quality of image restoration and generate clear images that are more in line with human vision, which is conducive to the improvement and practical application of wavefront coding systems.

Toward enriched decoding of mandarin spontaneous speech

A deep neural network (DNN)-based automatic speech recognition (ASR) method for enriched decoding of Mandarin spontaneous speech is proposed. It adopts an enhanced approach over the baseline model built with factored time delay neural networks (TDNN-f) and rescored with RNNLM to first building a baseline system composed of a TDNN-f acoustic model (AM), a trigram language model (LM), and a recurrent neural network language model (RNNLM) to generate a word lattice. It then sequentially incorporates a multi-task Part-of-Speech-RNNLM (POS-RNNLM), a hierarchical prosodic model (HPM), and a reduplication-word LM (RLM) into the decoding process by expanding the word lattice and performing rescoring to improve recognition performance and enrich the decoding output with syntactic parameters of POS and punctuation (PM), prosodic tags of word-juncture break types and syllable prosodic states, and an edited recognition text with reduplication words being eliminated. Experimental results on the Mandarin conversational dialogue corpus (MCDC) showed that SER, CER, and WER of 13.2 %, 13.9 %, and 19.1 % were achieved when incorporating the POS-RNNLM and HPM into the baseline system. They represented relative SER, CER, and WER reductions of 7.7 %, 7.9 % and 5.0 % as comparing with those of the baseline system. Futhermore, the use of the RLM resulted in additional 3 %, 4.6 %, and 4.5 % relative SER, CER, and WER reductions through eliminating reduplication words.

Scale-Hybrid Group Distillation with Knowledge Disentangling for Continual Semantic Segmentation.

Continual semantic segmentation (CSS) aims to learn new tasks sequentially and extract object(s) and stuff represented by pixel-level maps of new categories while preserving the original segmentation capabilities even when the old class data is absent. Current CSS methods typically preserve the capacities of segmenting old classes via knowledge distillation, which encounters the limitations of insufficient utilization of the semantic knowledge, i.e., only distilling the last layer of the feature encoder, and the semantic shift of background caused by directly distilling the entire feature map of the decoder. In this paper, we propose a novel CCS method based on scale-hybrid distillation and knowledge disentangling to address these limitations. Firstly, we propose a scale-hybrid group semantic distillation (SGD) method for encoding, which transfers the multi-scale knowledge from the old model's feature encoder with group pooling refinement to improve the stability of new models. Then, the knowledge disentangling distillation (KDD) method for decoding is proposed to distillate feature maps with the guidance of the old class regions and reduce incorrect guides from old models towards better plasticity. Extensive experiments are conducted on the Pascal VOC and ADE20K datasets. Competitive performance compared with other state-of-the-art methods demonstrates the effectiveness of our proposed method.

Simultaneous Recognition of Over- and Under-Expressed MicroRNAs Using Nanopore Decoding.

This paper describes a strategy for simultaneous recognition of over- and under-expressed microRNAs (miRNAs) using the method of signal classification-based nanopore decoding. MiRNA has attracted attention as a promising biomarker for cancer diagnosis owing to its cancer-type-specific expression patterns. While nanopore technology has emerged as a simple and label-free method to detect miRNAs and their expression patterns, recognizing patterns involving simultaneous over/under-expression is still challenging due to the inherent working principles. Here, inspired by the sequence design for DNA computation with nanopore decoding, we designed diagnostic DNA probes targeting two individual over/under-expressed miRNAs in the serum of oral squamous cell carcinoma. Through nanopore measurements, our designed probes exhibited characteristic current signals depending on the hybridized miRNA species, which were plotted on the scatter plot of duration versus current blocking ratio. The classified signals reflected the relative abundance of target miRNAs, thereby enabling successful pattern recognition of over/under-expressed miRNAs, even when using clinical samples. We believe that our method paves the way for miRNA-targeting simple diagnosis as a liquid biopsy.

Dynamic Weighted Filter Bank Domain Adaptation for Motor Imagery Brain–Computer Interfaces

A motor imagery (MI)-based brain–computer interface (BCI) is a promising system that can help neuromuscular injury patients recover or replace their motor abilities. Currently, before one uses MI-BCI, we need to collect a large amount of training data to train the decoding model, and this process is time consuming. When trained with a small amount of data, existing decoding methods generally do not perform well in MI decoding tasks. Therefore, it is important to improve the decoding performance with short calibration data. In this study, we propose a dynamic weighted filter bank domain adaptation framework that uses data from an existing subject to reduce the requirement of data from the new subject. A filter bank is used to explore information from different frequency subbands. A feature extractor with two 1-D convolutional layers is designed to extract EEG features. The class-specific Wasserstein generative adversarial network (WGAN)-based domain adaptation network aligns the distribution of each class between the data from the new subject and the data from the existing subject. Additionally, we apply an attention network to dynamically allocate different weights for different frequency bands. We evaluate our method on a public MI dataset and a self-collected dataset. The experimental results show that the proposed method achieves the best decoding accuracy among the compared methods with different amounts of training data. On the public dataset, our method achieves 8.88% and 7.16% higher decoding accuracy than the best comparing method with on block of training data on the two sessions, respectively. This indicates that our method can enhance MI decoding accuracy with a small amount of training data.

A VT-HMM-Based Framework for Countdown Timer Traffic Light State Estimation

Traffic lights are important components of traffic systems, and perceptual tasks on traffic lights are crucial for intelligent agents on the road. Auxiliary countdown timers, providing the remaining time of the current traffic phase, improve the safety and smoothness of the entire traffic system. This work proposes a state estimation framework for countdown timer traffic lights. Time-domain information is adequately integrated into a variable transition Hidden Markov Model (VT-HMM), and our system provides optimal estimates of traffic light colors and countdown numbers based on noisy detection inputs. A dynamic state transition matrix is designed based on a 1-step transition logic and a probability of the number of transitions related to the current state sojourn duration. A recursive decoding method based on the Viterbi algorithm is proposed to update all the state candidates and select the optimal state chain. Extensive experiments evaluate the robustness and effectiveness of the proposed work. The performance boundaries of this system are also found under various input noise levels. The source code is available here: https://github.com/ShuyangUni/countdown-timer-traffic-light-estimation

Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features.

Decoding human visual neural representations is a challenging task with great scientific significance in revealing vision-processing mechanisms and developing brain-like intelligent machines. Most existing methods are difficult to generalize to novel categories that have no corresponding neural data for training. The two main reasons are 1) the under-exploitation of the multimodal semantic knowledge underlying the neural data and 2) the small number of paired (stimuli-responses) training data. To overcome these limitations, this paper presents a generic neural decoding method called BraVL that uses multimodal learning of brain-visual-linguistic features. We focus on modeling the relationships between brain, visual and linguistic features via multimodal deep generative models. Specifically, we leverage the mixture-of-product-of-experts formulation to infer a latent code that enables a coherent joint generation of all three modalities. To learn a more consistent joint representation and improve the data efficiency in the case of limited brain activity data, we exploit both intra- and inter-modality mutual information maximization regularization terms. In particular, our BraVL model can be trained under various semi-supervised scenarios to incorporate the visual and textual features obtained from the extra categories. Finally, we construct three trimodal matching datasets, and the extensive experiments lead to some interesting conclusions and cognitive insights: 1) decoding novel visual categories from human brain activity is practically possible with good accuracy; 2) decoding models using the combination of visual and linguistic features perform much better than those using either of them alone; 3) visual perception may be accompanied by linguistic influences to represent the semantics of visual stimuli.

Classification algorithm for EEG-based motor imagery using hybrid neural network with spatio-temporal convolution and multi-head attention mechanism.

Motor imagery (MI) is a brain-computer interface (BCI) technique in which specific brain regions are activated when people imagine their limbs (or muscles) moving, even without actual movement. The technology converts electroencephalogram (EEG) signals generated by the brain into computer-readable commands by measuring neural activity. Classification of motor imagery is one of the tasks in BCI. Researchers have done a lot of work on motor imagery classification, and the existing literature has relatively mature decoding methods for two-class motor tasks. However, as the categories of EEG-based motor imagery tasks increase, further exploration is needed for decoding research on four-class motor imagery tasks. In this study, we designed a hybrid neural network that combines spatiotemporal convolution and attention mechanisms. Specifically, the data is first processed by spatiotemporal convolution to extract features and then processed by a Multi-branch Convolution block. Finally, the processed data is input into the encoder layer of the Transformer for a self-attention calculation to obtain the classification results. Our approach was tested on the well-known MI datasets BCI Competition IV 2a and 2b, and the results show that the 2a dataset has a global average classification accuracy of 83.3% and a kappa value of 0.78. Experimental results show that the proposed method outperforms most of the existing methods.

Experimental demonstration of a real-time multi-user uplink UWOC system based on SIC-free NOMA.

Non-orthogonal multiple access (NOMA) has been studied as a promising multiple access technology for optical communication systems due to its superior spectral efficiency. However, the multi-user communication systems that employ NOMA with successive interference cancellation (SIC) suffer from error propagation (EP). Besides, the issue of non-ideal rise and fall time of the received signal can result in severe bit error rate (BER) degradation while decoding by the SIC technique. In this paper, we propose a straightforward two-stage program judgment filter (PJF) for signal reshaping and a SIC-free decoding method for NOMA. Based on the amplitude threshold (AT) decoding method, we demonstrate a real-time, two-user uplink underwater wireless optical communication (UWOC) system via field programmable gate arrays (FPGAs). With a power allocation ratio (PAR) of 2:1 (user 1: user 2), the established real-time NOMA-based UWOC system utilizing commercial light emitting diodes (LEDs) achieves a data rate of 30 Mbps for each user with BERs of 7.8 × 10-6 and 3 × 10-4 for user 1 and user 2, respectively. The results show that the AT-based NOMA can obtain a lower BER compared to the SIC-based NOMA, especially for user 2.

Same but different: The latency of a shared expectation signal interacts with stimulus attributes

Predictive coding theories assert that perceptual inference is a hierarchical process of belief updating, wherein the onset of unexpected sensory data causes so-called prediction error responses that calibrate erroneous inferences. Given the functionally specialised organisation of visual cortex, it is assumed that prediction error propagation interacts with the specific visual attribute violating an expectation. We sought to test this within the temporal domain by applying time-resolved decoding methods to electroencephalography (EEG) data evoked by contextual trajectory violations of either brightness, size, or orientation within a bound stimulus. We found that following ∼170 ms post stimulus onset, responses to both size violations and orientation violations were decodable from physically identical control trials in which no attributes were violated. These two violation types were then directly compared, with attribute-specific signalling being decoded from 265 ms. Temporal generalisation suggested that this dissociation was driven by latency shifts in shared expectation signalling between the two conditions. Using a novel temporal bias method, we then found that this shared signalling occurred earlier for size violations than orientation violations. To our knowledge, we are among the first to decode expectation violations in humans using EEG and have demonstrated a temporal dissociation in attribute-specific expectancy violations.

GIS-BASED LANDSCAPE MANAGEMENT OF THE UZH RIVER BASIN: A STRATEGY TO ENHANCE RIVER WATER QUALITY

The article includes the findings of a study on the Uzh River basin’s surface water’s quality. This region is extremely important because a fraction of it is radioactively contaminated because of the Chornobyl nuclear power plant accident. Considering this, the goal of this work was to conduct a geo-informational analysis of the state and structure of the landscapes of the Uzh River basin, to identify the surface water quality parameters of this region, and to identify potential correlations between these parameters. For this purpose, we spatially divided the territory of the basin into separate massifs, in each of which, using the method of automatic decoding, we determined the ratio of the structural components of landscapes, their disturbance by erosion processes, and compared them with ground data on the quality of surface water of the massifs. According to the salt composition, all the investigated massifs have good quality conditions. The Uzh River and its tributaries should be categorized as 4 (slightly polluted) based on the average values of the trophosaprobological state, but the extreme values in some places shifted to 5 (moderately polluted). Most of the listed toxic substances were present at average levels and, for the most part, did not exceed the permitted concentrations for category 4-slightly polluted. Extreme concentrations frequently reached category 6 (polluted), which was primarily brought on by anthropogenic activity and the buildup of radioactive materials. It was found that the degree of erosive landscape destruction and the degree of landscape stabilization significantly influence the value of the integrated water quality index. Since the collected data, a three-dimensional model was developed, allowing for accurate evaluations and projections of changes in the quality of surface water based on the structural characteristics of the land shafts. Considering that some of these territories are currently in the zone of radioactive contamination, the planning of changes in the landscape structure should be coordinated with the potential risks of surface water quality deterioration, and the model proposed in this article will have significant applied value in addressing this issue.

The Optimization of Multi-objective FJSP Based on the Hybrid Algorithm

The flexible job-shop scheduling problem (FJSP) is a critical model in manufacturing systems that assigns operations from different jobs to various machines. However, optimizing multiple targets during the production scheduling process is always necessary. While the non-dominated sorting genetic algorithm (NSGA-II) is an effective method to solve the multi-objective FJSP, it can have the main drawbacks of converging too early and falling into local optimization. To address these issues, this research proposes a hybrid algorithm that combines NSGA-II and multi-objective simulated annealing using a pareto-domination based acceptance criterion (PDMOSA). The PDMOSA has a powerful search performance that can overcome the limitations of NSGA-II. The hybrid algorithm also includes original modification methods such as a deletion criterion, duplicated solution deletion, and new individual adding. Additionally, a plug-in decoding method is introduced. The proposed hybrid algorithm is compared with several improved ways based on NSGA-II in various experiments. The results demonstrate that the performance of the hybrid algorithm is better than the others in multi-objective FJSP.

Edge Intelligence-Assisted Asymmetrical Network Control and Video Decoding in the Industrial IoT with Speculative Parallelization

Industrial Internet of Things (IIoTs) has drawn significant attention in the industry. Among its rich applications, the field’s video surveillance deserves particular interest due to its advantage in better understanding network control. However, existing decoding methods are limited by the video coding order, which cannot be decoded in parallel, resulting in low decoding efficiency and the inability to process the massive amount of video data in real time. In this work, a parallel decoding framework based on the speculative technique is proposed. In particular, the video is first speculatively decomposed into data blocks, and then a verification method is designed to ensure the correctness of the decomposition. After verification, the data blocks having passed the validation can be decoded concurrently in the parallel computing platform. Finally, the concurrent decoding results are concatenated in line with the original encoding order to form the output. Experiments show that compared with traditional serial decoding ones, the proposed method can improve the performance by 9 times on average in the parallel computing environment with NVIDIA Tegra 4 chips, thus significantly enhancing the real-time video data’s decoding efficiency with guaranteed accuracy. Furthermore, proposed and traditional serial methods obtain almost the same peak signal-to-noise ratio (PSNR) and mean square error (MSE) metrics at different bit rates and resolutions, showing that the introduction of the speculative technique does not degrade the decoding accuracy.

Jump-GRS: a multi-phase approach to structured pruning of neural networks for neural decoding

Objective. Neural decoding, an important area of neural engineering, helps to link neural activity to behavior. Deep neural networks (DNNs), which are becoming increasingly popular in many application fields of machine learning, show promising performance in neural decoding compared to traditional neural decoding methods. Various neural decoding applications, such as brain computer interface applications, require both high decoding accuracy and real-time decoding speed. Pruning methods are used to produce compact DNN models for faster computational speed. Greedy inter-layer order with Random Selection (GRS) is a recently-designed structured pruning method that derives compact DNN models for calcium-imaging-based neural decoding. Although GRS has advantages in terms of detailed structure analysis and consideration of both learned information and model structure during the pruning process, the method is very computationally intensive, and is not feasible when large-scale DNN models need to be pruned within typical constraints on time and computational resources. Large-scale DNN models arise in neural decoding when large numbers of neurons are involved. In this paper, we build on GRS to develop a new structured pruning algorithm called jump GRS (JGRS) that is designed to efficiently compress large-scale DNN models. Approach. On top of GRS, JGRS implements a ‘jump mechanism’, which bypasses retraining intermediate models when model accuracy is relatively less sensitive to pruning operations. Design of the jump mechanism is motivated by identifying different phases of the structured pruning process, where retraining can be done infrequently in earlier phases without sacrificing accuracy. The jump mechanism helps to significantly speed up execution of the pruning process and greatly enhance its scalability. We compare the pruning performance and speed of JGRS and GRS with extensive experiments in the context of neural decoding. Main results. Our results demonstrate that JGRS provides significantly faster pruning speed compared to GRS, and at the same time, JGRS provides pruned models that are similarly compact as those generated by GRS. Significance. In our experiments, we demonstrate that JGRS achieves on average 9%–20% more compressed models compared to GRS with 2–8 times faster speed (less time required for pruning) across four different initial models on a relevant dataset for neural data analysis.

Maritime patrol tasks assignment optimization of multiple USVs under endurance constraint

Unmanned surface vehicles (USVs) are economic, have good maneuverability, and can perform some complex and high-risk tasks such as maritime supervision, leading to reduced costs and casualties. In this study, we investigate the application of USVs in maritime patrols, considering the endurance constraints of the USVs and the time constraints. Additionally, we establishes a mathematical model for optimizing the patrol path of multiple USVs under the endurance and time constraints. Considering the complexity of the model, the logistic map is introduced into the immune algorithm (IA) to improve the optimization. Then according to the relevant constraints, the corresponding coding and decoding methods are designed. Finally, the mutation and crossover operators of the genetic algorithm (GA) are combined with the designed IA to improve the diversity of antibodies in the iterative process, thereby improving the optimization ability of the algorithm. In the final numerical simulation experiment verification, the improved IA with GA (IA–GA) is compared with the traditional IA, GA, PSO-GA (Particle Swarm and Genetic hybrid algorithm) and IA–GA-greedy (IA–GA with greedy attribute) through simulations and case analysis. The results show that the improved IA can find a better solution than other algorithms in a reasonable time, which proves the superiority of the proposed algorithm.

Modeling and IAHA Solution for Task Scheduling Problem of Processing Crowdsourcing in the Context of Social Manufacturing

The paper addresses the discrete characteristics of the processing crowdsourcing task scheduling problem in the context of social manufacturing, divides it into two subproblems of social manufacturing unit selecting and subtask sorting, establishes its mixed-integer programming with the objective of minimizing the maximum completion time, and proposes an improved artificial hummingbird algorithm (IAHA) for solving it. The IAHA uses initialization rules of global selection, local selection, and random selection to improve the quality of the initial population, the Levy flight to improve guided foraging and territorial foraging, the simplex search strategy to improve migration foraging to enhance the merit-seeking ability, and the greedy decoding method to improve the quality of the solution and reduce solution time. For the IAHA, orthogonal tests are designed to obtain the optimal combination of parameters, and comparative tests are made with variants of the AHA and other algorithms on the benchmark case and a simulated crowdsourcing case. The experimental results show that the IAHA can obtain superior solutions in many cases with economy and effectiveness.

SKDCPM algorithm can improve the single-trial decoding performance of very similar error-related potentials.

Error related potential (ErrP) is an effective control signal for the brain-computer interface (BCI). Current ErrP decoding methods can only distinguish right and wrong mental states. However, in real scenarios, error conditions often contain more detailed information, such as the degree of error, which would induce very similar ErrPs. Distinguishing such ErrPs effectively is of vital importance to provide more detailed information for optimizing BCIs. Hereto, a major challenge is the EEG differences of very similar ErrPs are very small. Thus, it is necessary to develop new efficient method for decoding very similar ErrPs. This study newly proposed an algorithm named shrinkage discriminant canonical pattern matching (SKDCPM), and compared its decoding results with the linear discriminant analysis (LDA), shrinkage LDA (SKLDA), stepwise LDA (SWLDA), Bayesian LDA (BLDA) and the DCPM, which were algorithms commonly used for ErrP decoding. A data set of 18 subjects was built, it had four conditions, i.e., right (0°), errors with varying degrees, i.e., 45°, 90°, 180° deviation from the predicted direction. As a result, the SKDCPM had high balanced accuracy (BACC) in right-wrong classification (0° vs. others). More importantly, it achieved a grand averaged BACC of 69.54% with the highest up to 74.25%, which outperformed all the other algorithms in very similar ErrPs decoding (45° vs. 90° vs. 180°) significantly. This study could provide new decoding methods for developing the ErrP-based BCI system.

Enhanced Pedestrian Navigation on Smartphones With VLP-Assisted PDR Integration

Pedestrian dead-reckoning (PDR) is a potential indoor localization technology that utilizes the inertial measurement unit (IMU) to estimate location. However, one of its most significant drawbacks is the accumulation measurement error. This paper proposes a PDR system integrated with visible light positioning (VLP) that boasts low accumulated error and can achieve real-time and accurate indoor positioning using both the IMU and the camera sensor on a smartphone. A multi-frame fusion method for LED-ID decoding is introduced in the encoding and decoding process of the system, achieving 98.5% decoding accuracy with a 20-bit-long LED-ID at the height of 2.1 m. This method also accommodates the variation in the shutter speeds of cameras and heights of the LED. Meanwhile, absolute locations and step length could be further calibrated using a single light-emitting diode (LED), providing an average accuracy within 0.5 meters over a 108-meter walk.