Training Sequence Research Articles

Reservoir Computing Meets Extreme Learning Machine in Real-Time MIMO-OFDM Receive Processing

In this paper, we consider a real-time deep learning-based symbol detection approach for MIMO-OFDM systems. To exploit the temporal correlation of the wireless channel and the time-frequency structure of OFDM signals, a recurrent neural network (RNN) with deep feedforward output layers is introduced, where the recurrent layers and feedforward output layers are designed to process time-domain and frequency-domain information respectively. Reservoir computing (RC), a special type of RNN, and extreme learning machine (ELM), a special type of feedforward neural network, are chosen as the corresponding building blocks to facilitate over-the-air training. An online training loss objective is introduced to recursively update the neural weights in real-time. We believe this is the first work in the literature to realize real-time machine learning for MIMO-OFDM symbol detection, i.e., conducting NN-based symbol detection on an OFDM symbol basis. We demonstrate that (1) the <i>IEEE</i> standardized WiFi training sequence can be directly applied as the real-time training sequence (2) the symbol detection performance can be further improved by using our theoretically derived pilot pattern. Evaluation results show that our RC-ELM-based symbol detection method outperforms traditional model-based techniques as well as state-of-the-art learning-based approaches in highly dynamic channel environments for real-time symbol detection.

Analysis on Optimal Error Exponents of Binary Classification for Source with Multiple Subclasses

We consider a binary classification problem for a test sequence to determine from which source the sequence is generated. The system classifies the test sequence based on empirically observed (training) sequences obtained from unknown sources and . We analyze the asymptotic fundamental limits of statistical classification for sources with multiple subclasses. We investigate the first- and second-order maximum error exponents under the constraint that the type-I error probability for all pairs of distributions decays exponentially fast and the type-II error probability is upper bounded by a small constant. In this paper, we first give a classifier which achieves the asymptotically maximum error exponent in the class of deterministic classifiers for sources with multiple subclasses, and then provide a characterization of the first-order error exponent. We next provide a characterization of the second-order error exponent in the case where only has multiple subclasses but does not. We generalize our results to classification in the case that and are a stationary and memoryless source and a mixed memoryless source with general mixture, respectively.

GMM based low-complexity adaptive machine-learning equalizers for optical fiber communication

The demand for high-speed data transmission has increased rapidly over the past few years, leading to advanced optical communication techniques. However, most of machine learning based equalizers which are trained with offline dataset mainly focus on achieving low BER, neglecting the generalization ability when the properties of optical link change. In this paper, we propose Gaussian Mixture model (GMM) based low-complexity adaptive machine-learning equalizers. The proposed online training strategy can fine-tune the parameters in GMM with a small amount of training sequence by introducing Maximum a posteriori probability (MAP) algorithm and sliding window. The size of online training sequence can be reduced by utilizing the parameters trained from offline data as the priori information to reduce the size of online training sequence. The proposed adaptive GMM based equalizers can not only show an excellent capability of mitigating nonlinear distortions but also show the ability to update parameters automatically according to the channel conditions. In addition, experimental results show that by introducing MAP algorithm and sliding window, the convergence speed of the proposed equalizers have been accelerated by 2 times, compared with the case that the traditional Expectation Maximization (EM) algorithm is used for online parameter update. On the other hand, there is no significant increase in computational complexity during the online stage.

Predicting binding affinities of emerging variants of SARS-CoV-2 using spike protein sequencing data: observations, caveats and recommendations

Predicting protein properties from amino acid sequences is an important problem in biology and pharmacology. Protein-protein interactions among SARS-CoV-2 spike protein, human receptors and antibodies are key determinants of the potency of this virus and its ability to evade the human immune response. As a rapidly evolving virus, SARS-CoV-2 has already developed into many variants with considerable variation in virulence among these variants. Utilizing the proteomic data of SARS-CoV-2 to predict its viral characteristics will, therefore, greatly aid in disease control and prevention. In this paper, we review and compare recent successful prediction methods based on long short-term memory (LSTM), transformer, convolutional neural network (CNN) and a similarity-based topological regression (TR) model and offer recommendations about appropriate predictive methodology depending on the similarity between training and test datasets. We compare the effectiveness of these models in predicting the binding affinity and expression of SARS-CoV-2 spike protein sequences. We also explore how effective these predictive methods are when trained on laboratory-created data and are tasked with predicting the binding affinity of the in-the-wild SARS-CoV-2 spike protein sequences obtained from the GISAID datasets. We observe that TR is a better method when the sample size is small and test protein sequences are sufficiently similar to the training sequence. However, when the training sample size is sufficiently large and prediction requires extrapolation, LSTM embedding and CNN-based predictive model show superior performance.

Research on Mongolian-Chinese Neural Machine Translation Based on CSGAN and Co-training

Abstract Aiming at the problems of poor translation quality and scarcity of Mongolian-Chinese parallel corpus resources in Mongolian-Chinese neural machine translation, this paper proposes a method based on conditional sequence of generative adversarial networks (CSGAN) and collaborative training. This method uses the CSGAN network based on adversarial training to train the translation model and obtains a better translation. At the same time, in order to make full use of the existing corpus resources, a collaborative training method is adopted on the basis of the above translation model to integrate the translation into the translation results of the high-resource corpus, and further improve the performance of Mongolian-Chinese machine translation. By comparing the BLEU values of different translation models, it is shown that using CSGAN-based and collaborative training methods can significantly improve the quality of Mongolian-Chinese translation models.

Audio Scene Monitoring Using Redundant Ad Hoc Microphone Array Networks

We present a system for localizing sound sources in a room with several ad-hoc microphone arrays. Each circular array performs direction of arrival (DOA) estimation independently using commercial software. The DOAs are fed to a fusion center, concatenated, and used to perform the localization based on two proposed methods, which require only few labeled source locations (anchor points) for training. The first proposed method is based on principal component analysis (PCA) of the observed DOA and does not require any knowledge of anchor points. The array cluster can then perform localization on a manifold defined by the PCA of concatenated DOAs over time. The second proposed method performs localization using an affine transformation between the DOA vectors and the room manifold. The PCA has fewer requirements on the training sequence, but is less robust to missing DOAs from one of the arrays. The methods are demonstrated with five IoT 8-microphone circular arrays, placed at unspecified fixed locations in an office. Both the PCA and the affine method can easily map out a rectangle based on a few anchor points with similar accuracy. The proposed methods provide a step towards monitoring activities in a smart home and require little installation effort as the array locations are not needed.

High-Capacity Space-Division Multiplexing Communications With Silicon Photonic Blind Source Separation

Space-division multiplexing is a widely used technique to improve data-carrying capacities in both wireless and optical communication systems. However, tightly packed spatial channels cause severe crosstalk. High data rates and large channel counts impose severe constraints on resolving the crosstalk using traditional digital signal processing algorithms and electronic circuits. In order to solve these issues, this paper presents a silicon photonic system combining high-speed silicon photonic devices with a novel blind source separation (BSS) algorithm. We first demonstrate using photonic BSS to undo modal crosstalk in a short-reach multimode optical fiber interconnect for intra-data-center communications. The proposed photonic BSS system inherits the advantages of photonic matrix processor and the “blindness” of BSS, leading to superior energy and cost efficiency and reduced latency, while allowing to recover the signals using a sub-Nyquist sampling rate and in a free-running mode, and offering unmatched agility in signal format and data rate. The feasibility of using photonic processors for mode crosstalk equalization has been recently demonstrated, assisted with training sequences. Our approach, photonic BSS, in contrast, can tackle the more difficult problem of making the receiver transparent to any data rate and modulation format, and workable with slow and cost-effective electronics. In addition, we find that photonic BSS has a much better scaling law for space-division multiplexing (SDM)-based communication systems than digital signal processing (DSP). When compared to state-of-the-art DSP, photonic BSS can reduce system power consumption, speed, and latency by several orders of magnitude, particularly for high-capacity communications with high data rates per channel and a large number of channels. Photonic BSS has the added advantages of being agnostic to transmission content, making it exceptional at protecting communication privacy. This paper also discusses our previous work in demonstrating photonic BSS for privacy protection in wireless multiple-in multiple-out (MIMO) communications using silicon photonic micoring resonator (MRR) weight banks.

Accurate Channel Estimation and Adaptive Underwater Acoustic Communications Based on Gaussian Likelihood and Constellation Aggregation

Achieving accurate channel estimation and adaptive communications with moving transceivers is challenging due to rapid changes in the underwater acoustic channels. We achieve an accurate channel estimation of fast time-varying underwater acoustic channels by using the superimposed training scheme with a powerful channel estimation algorithm and turbo equalization, where the training sequence and the symbol sequence are linearly superimposed. To realize this, we develop a ‘global’ channel estimation algorithm based on Gaussian likelihood, where the channel correlation between (among) the segments is fully exploited by using the product of the Gaussian probability-density functions of the segments, thereby realizing an ideal channel estimation of each segment. Moreover, the Gaussian-likelihood-based channel estimation is embedded in turbo equalization, where the information exchange between the equalizer and the decoder is carried out in an iterative manner to achieve an accurate channel estimation of each segment. In addition, an adaptive communication algorithm based on constellation aggregation is proposed to resist the severe fast time-varying multipath interference and environmental noise, where the encoding rate is automatically determined for reliable underwater acoustic communications according to the constellation aggregation degree of equalization results. Field experiments with moving transceivers (the communication distance was approximately 5.5 km) were carried out in the Yellow Sea in 2021, and the experimental results verify the effectiveness of the two proposed algorithms.

Constructing benchmark test sets for biological sequence analysis using independent set algorithms.

Biological sequence families contain many sequences that are very similar to each other because they are related by evolution, so the strategy for splitting data into separate training and test sets is a nontrivial choice in benchmarking sequence analysis methods. A random split is insufficient because it will yield test sequences that are closely related or even identical to training sequences. Adapting ideas from independent set graph algorithms, we describe two new methods for splitting sequence data into dissimilar training and test sets. These algorithms input a sequence family and produce a split in which each test sequence is less than p% identical to any individual training sequence. These algorithms successfully split more families than a previous approach, enabling construction of more diverse benchmark datasets.

Doppler Mitigation Method Aided by Reconfigurable Intelligent Surfaces for High-Speed Channels

Reconfigurable intelligent surface (RIS) is an attractive solution to smart radio environment, which has a promising potential to mitigate Doppler effect for mobile channels. In this letter, we present a Doppler mitigation method assisted by RIS for high-speed scenarios, including the design of transmission protocol and the phase control of RIS pattern. The transmission protocol is an enhanced version of a two-stage protocol. A two-phase training sequence is introduced in the first stage, to decouple the estimates of direct and cascaded channels and simplify the training matrix for LS estimation. Training overheads are reduced in the second stage to improve the data rate. In addition, the real-time control matrix of the RIS pattern is provided for Doppler mitigation. Numerical simulations show that the presented method can effectively mitigate Doppler shift, and improve the achievable rate to be 1.82-fold.

Dependency syntax guided BERT-BiLSTM-GAM-CRF for Chinese NER

Traditional named entity recognition (NER) methods derived from deep learning (DL) often ignore the long-distance syntactic dependence relationships between words. In such methods, the representation of Chinese word vectors is too simple to solve the problem of polysemy. To address these shortcomings, this paper proposes a syntactic dependency guided BERT-BiLSTM-GAM-CRF model for Chinese NER. First, the self-attention method guided by the dependency syntactic parsing tree is embedded in the transformer computing framework of the BERT model. This can not only obtain the deep two-way linguistic representation of a word according to the context information of the word, but it can also better express the long-distance syntactic dependency relationships between words; Second, the trained word vector sequence is input into the BiLSTM layer embedded in the global attention mechanism (GAM), and then the most important whole situation semantic information in the sentence is obtained. Finally, the CRF is employed to learn the dependence relationships between adjacent labels to obtain the best sentence level label sequence. A large number of experiments on the CLUENER-2020 corpus, MSRA corpus, Weibo corpus and OntoNotes4 corpus prove that the constructed model has good results for the Chinese NER task, and the F1 values are 81.08%, 94.97%, 63.60% and 75.64% respectively.

Training Optimization for Subarray-Based IRS-Assisted MIMO Communications

In this article, we investigate the training optimization for multiple-input–multiple-output (MIMO)-aided Internet of Things (IoTs) systems that employ subarray-based intelligent reflecting surface (IRS). In order to overcome the nonlinear relationship between two cascaded channel matrices, the IRS can be divided into a series of subarrays, for which only an equivalent cascaded channel matrix should be estimated in each subarray. Correspondingly, the training sequence should be divided into multiple segments. By sufficiently utilizing the available statistical channel state information (CSI), either mean-square error (MSE) minimization or mutual information (MUI) maximization can be taken as the performance metric for optimizing the training sequence. A variety of fairnesses among different subarray channel estimations has been taken into account. Furthermore, in order to reduce the hardware cost of the power amplifier, we propose a two-stage training sequence structure, including a fully digital filter and a constant modulus sequence. To further reduce computational complexity, various low-complexity water-filling solutions are proposed. Numerical results demonstrate the accuracy and efficiency of the proposed solutions.

Some remarks on Bayesian multiple hypothesis testing

We consider Bayesian multiple hypothesis problem with independent and identically distributed observations. The classical, Sanov's theorem-based, analysis of the error probability allows one to characterize the best achievable error exponent. However, this analysis does not generalize to the case where the true distributions of the hypothesis are not exact or partially known via some nominal distributions. This problem has practical significance, because the nominal distributions may be quantized versions of the true distributions in a hardware implementation, or they may be estimates of the true distributions obtained from labeled training sequences as in statistical classification. In this paper, we develop a type-based analysis to investigate Bayesian multiple hypothesis testing problem. Our analysis allows one to explicitly calculate the error exponent of a given type and extends the classical analysis. As a generalization of the proposed method, we derive a robust test and obtain its error exponent for the case where the hypothesis distributions are not known but there exist nominal distribution that are close to true distributions in variational distance.

Toward MR-only proton therapy planning for pediatric brain tumors: Synthesis of relative proton stopping power images with multiple sequence MRI and development of an online quality assurance tool.

To generate synthetic relative proton stopping power (sRPSP) images from magnetic resonance imaging (MRI) sequence(s) and develop an online quality assurance (QA) tool for sRPSP to facilitate safe integration of magnetic resonance (MR)-only proton planning into clinical practice. Planning computed tomography (CT) and MR images of 195 pediatric brain tumor patients were utilized (training: 150, testing: 45). Seventeen consistent-cycle generative adversarial network (ccGAN) models were trained separately using paired CT-converted RPSP and MRI datasets to transform a subject's MRI into sRPSP. T1-weighted (T1W), T2-weighted (T2W), and FLAIR MRI were permutated to form 17 combinations, with or without preprocessing, for determining the optimal training sequence(s). For evaluation, sRPSP images were converted to synthetic CT (sCT) and compared to the real CT in terms of mean absolute error (MAE) in Hounsfield units (HU). For QA, sCT was deformed and compared to a reference template built from training dataset to produce a flag map, highlighting pixels that deviate by >100HU and fall outside the mean±standard deviation reference intensity. The gamma intensity analysis (10%/3mm) of the deformed sCT against the QA template on the intensity difference was investigated as a surrogate of sCT accuracy. The sRPSP images generated from a single T1W or T2W sequence outperformed that generated from multi-MRI sequences in terms of MAE (all p<0.05). Preprocessing with N4 bias and histogram matching reduced MAE of T2W MRI-based sCT (54±21HU vs. 42±13HU, p=0.002). The gamma intensity analysis of sCT against the QA template was highly correlated with the MAE of sCT against the real CT in the testing cohort (r=-0.89 for T1W sCT; r=-0.93 for T2W sCT). Accurate sRPSP images can be generated from T1W/T2W MRI for proton planning. A QA tool highlights regions of inaccuracy, flagging problematic cases unsuitable for clinical use.

Understanding the rehabilitation psychology specialty career pathway.

Little is known about how psychologists choose their specialty practice area, and rehabilitation psychology is no exception. Specialization and specialty certification in professional psychology have been controversial topics impacting the field during the training sequence and across the span of professional careers (Drum & Blom, 2001; Robiner & Fossum, 2017). The American Board of Rehabilitation Psychology (ABRP) has been providing specialty certification since 1995 and rehabilitation psychology was recognized as a unique specialty in 2015 by the APA's Council for the Recognition of Specialties and Proficiencies in Professional Psychology (CRSPPP). There are limited established training programs and minimal information about the specialty in undergraduate course materials. The current survey is intended to provide information about how people are introduced to the field of rehabilitation psychology, specialty identification, and to identify opportunities for improvement. A survey of members of APA Division 22 and ABRP specialists was conducted to collect information about their exposure to and involvement in rehabilitation psychology. Results from 174 respondents suggest that personal relationships are the current key means of recruitment and confirms that rehabilitation psychology has limited presence in undergraduate training. Most professionals come to identify with rehabilitation psychology after training in clinical neuropsychology and health psychology. These preliminary results suggest that the current generalist training sequence does not provide sufficient exposure to, or preparation for the field of rehabilitation psychology. Recruitment opportunities should emphasize student leadership network activities and the identification of early and midcareer practitioners unaware of the rehabilitation specialty. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

How Not to Be an Expert

How <i>Not</i> to Be an Expert

Integrated Frame Coding for Short Burst Transmission in Mobile Visible Light Communication Systems

Recently, visible light communication (VLC) has become a promising option for secure data transmission in industrial Internet of Things (IIoTs). In IIoT-VLC systems, small attocells are adopted to achieve higher spatial reuse rate, and the transmission of data, control and feedback bursts often requires high efficiency and real-time feature. Conventionally, multi-field (MF) frames are used in VLC systems which consists of sync header, channel training sequence, check field, etc. in addition to data payload. However, for short burst transmission, MF frames could result in efficiency loss and latency increase due to useless padding bits. In this paper, a novel coding scheme named integrated frame code (IFC) in physical layer to realize efficient and real-time transmission simultaneously is presented. IFC scheme reduces latency by simplifying transmission procedure and decreases overhead redundancy by integrated design. Specifically, we propose a joint soft-decision criterion for receiving without separate synchronization and channel estimation and then analyze its error performance. After that, we present IFC construction criterion and two design examples. At last, simulation results confirm that for short burst transmission, IFC achieves better efficiency and robustness than MF especially in moving process.

Joint monitoring of OSNR and frequency offset for coherent optical fiber communication systems based on QPSK training sequence

We propose a joint monitoring scheme of optical signal-to-noise ratio (OSNR) and frequency offset (FO) based on the analysis of a quadrature phase-shift keying training sequence (QPSK-TS) spectrum for coherent optical fiber communication systems. In the proposed scheme, the FO estimation (FOE) consists of a coarse FOE stage and a fine FOE stage. Firstly, the coarse FOE stage is operated by searching for the peak of QPSK-TS spectrum. Then, after conducting coarse FO compensation (FOC) and down-sampling process to the QPSK-TS signal, the fine FOE stage can be realized by operating fast Fourier transform (FFT) to the 4th power of the signal. Compared with the traditional FOE scheme based on FFT with 4th-power operation, the FOE range of the proposed scheme can be extended to 3 times without losing the FOE resolution. After the FOC procedure with the proposed FOE scheme, OSNR can be monitored accurately by obtaining the whole in-band amplified spontaneous emission (ASE) noise from QPSK-TS spectrum. It is noteworthy that both the proposed FOE scheme and the OSNR monitoring scheme are insensitive to chromatic dispersion (CD) and intra-channel nonlinearity (NL). Simulation results for a 28 GBaud system with 2400 km transmission length show that when the OSNR range is 10∼28 dB and FO is 10.25 GHz, the mean OSNR estimated error is < 0.9 dB and the standard deviation is < 0.3 dB. Furthermore, the back-to-back (B2B) experiment results with 20 GBaud show that when the OSNR range is 10∼26 dB and FO is 7 GHz, the mean OSNR estimated error is < 0.8 dB and the standard deviation is also < 0.3 dB.

Structure Optimization of Mixed-Speed Train Traffic for Cyclic Timetable: Model and Algorithm Development

Trains can be optimally spread over the period of the cyclic timetable. By integrating sequencing issue with headway time together, this paper studies the structure optimization of mixed-speed train traffic for a cyclic timetable. Firstly, by taking it as a job-shop problem with sequence-dependent setup times on one machine, in the type of infinite capacity resource with headway (ICR + H), the problem is transformed to alternative graph (AG) and then recast to the mixed-speed train traffic planning (MSTTP) model. For the multiobjective in MSTTP, three indicators are optimized, i.e., heterogeneity, cycle time, and buffer time, which correspond to diversity of train service toward passenger, capacity consumption of rail network, and stability of train operation, respectively. Secondly, the random-key genetic algorithm (RKGA) is proposed to tackle the sequence and headway simultaneously. Finally, RKGA is coded with visual studio C# and the proposed method is validated with a case study. The rail system considered is a line section encompassing a territory of 180 km with 15 mixed-speed trains in each cycle of the timetable. Results indicate the comprehensively balanced train plan for all stakeholders from random variations of train sequence and headway time. Both the quantitative proportion of heterogeneity/homogeneity (e.g., 2.5) about the optimized distribution of the mixed train traffic and the link between train headway time and the sequence for each traffic scenario are found. All the findings can be used to arrange the mixed-speed train traffic more scientifically.

Effect of intensity sequence of resistance training on some antioxidants factors and Malondialdehyde plasma in over weight men

Background and Aims: Todays, many factors and variables are considered in the design of resistance training that may affect physiological adaptations. Despite the positive effect of resistance training on antioxidant behavior and oxidative stress, the influents of these factors to intensity sequence of resistance training is unclear. The purpose of this study was to determine the effects of resistance training intensity sequence of resistance training on antioxidants and Malondialdehyde (MDA) in over weight men. Methods: In present semi experimental study, 30 over weight young males voluntarily participated in the study and randomly assigned to pyramid resistance training (PRT; n=10), reverse pyramid resistance training (RPRT; n=10), and control (n=10). Resistance training was done in 3 nonconsecutive days for eight weeks, where the PRT was done resistance training by gradually increasing the intensity and decreasing the number of repetitions to reach maximum strength, while the RPRT they did the exact opposite. Blood samples were collected before and 48 after exercise training, and superoxide dismutase (SOD), Malondialdehyde (MDA), glutathione peroxidase (GPX), and total Antioxidant capacity (TAC) were measured by McCord &amp; Fridovich, Buege&amp; Aust, Paglia &amp; valentine and FARP methods, respectively. In order to analyze the data, analysis of variance was used with repeated measurements. Results: It was observed that SOD in the PRT (p=0.024) and the RPRT (p=0.029) increased significantly. The GPX in the PRT (p=0.008) and RPRT (p=007) than to control were also significantly increased. Also, the TAC increased significantly only in the PRT (p=0.047). The MDA in the PRT (p=0.019) and the RPRT (p=0.041) were significantly decrease, no significant difference was observed between PRT and RPRT in any of the mentioned variables (p˃0.05). Conclusion: Based on the results of the study, it seems that pyramid and reverse pyramid resistance training can improve the antioxidant status in overweight men, however, they have not any advantages than to each other.