Data Block Research Articles

Distributed random vector functional link network with subspace-based local connections

In order to solve the problem of poor generalization ability and high computational complexity of random vector functional link (RVFL) network when dealing with large-scale data classification, we design and implement a distributed RVFL network with subspace-based local connections in Spark framework (DRVFL-SLC). Firstly, in order to take advantage of the partition parallelism of resilient distributed dataset (RDD), the large-scale dataset stored in the Hadoop distributed file system HDFS is randomly divided into random sample partition (RSP) data blocks and each RSP data block corresponds to a partition of the RDD, where the RSP data block is a subset of data that maintains probability distribution consistency with the big data at a given significance level. After that, the mapPartitions transformation is invoked on the RDD containing multiple partitions in a distributed environment and this operation trains the corresponding optimal RVFL-SLC efficiently in parallel. Then, the collect execution operator is used to efficiently fuse the optimal RVFL-SLC corresponding to each partition of the RDD to obtain DRVFL-SLC for realizing the classification of big data. Finally, the feasibility and effectiveness of DRVFL-SLC are verified based on several large-scale data set with at least million records on a Spark cluster deployed with 6 computing nodes. The results show that DRVFL-SLC has a good speedup ratio, scalability and scale growth, and can achieve better generalization performance than RVFL-SLC trained on a single machine with full data.

Adaptation of Range-Doppler Algorithm for Efficient Beamforming of Monostatic and Multistatic Ultrasound Signals.

Algorithmic changes that increase beamforming speed have become increasingly relevant to processing synthetic aperture (SA) ultrasound data. In particular, beamforming SA data in a spatio-temporal frequency domain using the F-k (Stolt) migration have been shown to reduce the beamforming time by up to two orders of magnitude compared with the conventional delay-and-sum (DAS) beamforming, and it has been used in applications where large amounts of raw data make real-time frame rates difficult to attain, such as multistatic SA imaging and plane-wave Doppler imaging with large ensemble lengths. However, beamforming signals in a spatio-temporal Fourier space can require loading large blocks of data at once, making it memory-intensive and less suited for parallel (i.e., multithreaded) processing. As an alternative, we propose beamforming in a range-Doppler (RD) frequency domain using the range-Doppler algorithm (RDA) that has originally been developed for SA radar (SAR) imaging. Through simulation and phantom experiments, we show that RDA achieves similar lateral resolution and contrast compared with DAS and F-k migration. At the same time, higher axial sidelobes in RDA images can be reduced via (temporal) frequency binning. Like the F-k migration, RDA significantly reduces the overall number of computations relative to DAS, and it achieves ten times lower processing time on a single CPU. Because RDA uses only a spatial Fourier transform (FT), it requires two times less memory than the F-k migration to process the simulated multistatic data and can be executed on as many as a thousand parallel threads (compared with eight parallel threads for the F-k migration), making it more suitable for implementation on modern graphics processing units (GPUs). While RDA is not as parallelizable as DAS, it is expected to hold a significant speed advantage on devices with moderate parallel processing capabilities (up to several thousand cores), such as point-of-care and low-cost ultrasound devices.

Laboratory assessment of state of post-vaccination humoral immunity to infections with aerosol transmission mechanism

The review considers questions about the place of laboratory diagnostics in preventive medicine, in particular, about the possibilities of using laboratory methods in controlling the vaccination of infections with an aerosol transmission mechanism (measles, rubella, mumps, chickenpox, influenza, pneumococcal infection, pertussis, diphtheria, COVID-19). The article highlights the main laboratory methods of seromonitoring (enzyme immunoassay, radial hemolysis reaction in gel, dot-immunoassay, antibody avidity determination, hemagglutination inhibition reaction, microneutralization reaction, FAMA, plaque suppression reaction), their advantages and disadvantages. Also presented a block of data on alternative biomarkers (enzymes, lipids, trace elements, hormones, etc.). which serve as potential predictors of vaccination efficacy. The search for new biomarkers of the effectiveness of the formation of post-vaccination immunity opens up new possibilities for predicting the effectiveness of vaccination, which makes their study a promising direction in the field of vaccinology and laboratory immunology.

Variable selection and data fusion for diesel cetane number prediction

This study evaluates the potential of variable selection to improve the performance of data fusion modelling to estimate diesel cetane number from NIR spectroscopy information acquired on total effluent samples obtained from the hydrocracking process and their operating variables. The evaluation conducted in this research was divided into four steps. First, predictive models were developed using each data block separately. Next, seven variable selection methods were applied on the NIR block, and eleven methods were applied on the process variable block. Then, with each data set generated from the variable selection analysis, single prediction models were generated and compared with those developed in the first step. Finally, data fusion was performed once the best variable selection method was defined for each data block. Two data fusion models were generated, a first using all the variables in the two blocks and a second using only the previously selected variables. In addition, the potential of the sequential and orthogonalized covariance selection (SO-CovSel) method was also analyzed. The results showed that the data fusion modelling using all variables from each data block improves the estimation of the diesel cetane number compared to single models (about 20% reduction of the RMSEP). However, using variable selection analysis before data fusion significantly improves the estimation of this property and leads to greater model stability regarding the RMSE's and r′s (about 47% of the RMSEP). The Covariance Selection (CovSel) method was the most efficient in the NIR data block, while for the process variable data block, it was the sequential backward floating feature selection method (SBFFS) that gave the best performance. The advantages offered by the variable selection resulted not only in having a more accurate prediction of the property but also in improving the analysis and understanding of the process by determining the variables that significantly impact the property studied.

The network society in the ‘new normal times’: Crisis digitalization and adaption of cultural organizations in the COVID-19

For the recent 3 years, there has been a growing research interest in adaptation to the new normality and crisis digitalization during pandemic. However, there are a little empirical researches in cultural organizations. This study is in line with some sorts of approaches of network society and autonomy. The aim of the research is to study how cultural institutions integrate into the network society through one of the critical elements in creating a network society – digitalization during COVID-19 pandemic. The study was conducted using a mixed methodology in 2021 in St. Petersburg. Three blocks of empirical data were collected and analyzed based on theaters, museums, libraries, and creative spaces: 67 questionnaires; 12 expert interviews; webometrics of social networks of 108 organizations. The key difficulties were the weakness of the technical base and the lack of competencies and specialists to produce content and attract an audience online. The key findings are three strategies of adaptation to the conditions of the new normality: deepening digitalization; hybrid and strategy of autonomy from digitalization. The strategy of deepening digitalization is typical mainly for libraries that are active online even before the pandemic. They found themselves in the most advantageous position by building and expanding the previously developed digital activity. The hybrid strategy was mainly characteristic of museums, which intensified the digitization of collections and introduced new formats, including broadcasts from previously closed repositories. The strategy of autonomy from digitalization is more inherent in theaters, for which the transition to online turned out to be the most difficult and in many cases impossible. Crisis digitalization has exposed the structural difficulties associated with (non-)willingness to transform the former autonomy into the new requirements of the network society.

Differential Analysis of a Cryptographic Hashing Algorithm HBC-256

The article observes the new hashing algorithm HBC-256. The HBC-256 algorithm is based on the block cipher of the compression function CF (Compression Function) and produces a 256-bits hash value. Like any new cryptographic structure, the HBC-256 algorithm requires careful research process in order to confirm its cryptographic properties, namely: pre-image resistance and resistance to collisions of the first and second order. As a result of the research, for the HBC-256 hashing algorithm differential properties of nonlinear elements (S-boxes) and various options for constructing round characteristics are considered. A hypothesis has been advanced about the existence of paired differences, which will make it possible to construct round characteristics for hashing and for the function of round keys generating. It is shown that even for the most optimal way of constructing chains of differences, the probability of finding correct pairs of texts is less than the probability of a complete enumeration of one 128-bit block of input data, which makes the method of differential cryptanalysis unsuitable for finding collisions.

Tensor partial least squares for hyperspectral image classification

A hyperspectral image is classically a three-way (or tensor) block of data. In order to extract information from it, it has to be classified using image classifiers. Since classifiers are traditionally two-way classifiers, the hyperspectral data is unfolded into a two-way data. Processing the hyperspectral data as a two-way data often reduces the accuracy of the classification. This research explores the novel application of Tensor Partial Least Squares (TPLS) for hyperspectral image classification. TPLS has been proven to be more robust than the two-way PLS. Unlike the two-way classifiers, the TPLS utilises the hyperspectral data as a three-way (tensor) data. Two hyperspectral images of Indian Pines region in Northwest Indiana, USA and University of Pavia, Italy are used as test beds for the experiment. The results extracted by the model are the X loadings, Y loadings, X scores, and Y scores. The computed training mean r square values for Indian Pines and University of Pavia are 0.9061 ± 0.74 , and 0.9155 ± 0.63 respectively. The results of the experiment show that the TPLS performed better than the unfolded PLS, but fell short of the notable traditional classifiers.

A Near-Optimal Truthful Online Auction for Efficient Crowdsourced Data Trading with Dynamic Data Owners and Dynamic Data Requests

Data is an extremely important asset in a modern scientific and commercial society. The life force behind powerful artificial intelligence (AI) or machine learning (ML) algorithms is data, especially lots of data, which makes data trading significantly essential to unlocking the power of AI or ML. Data owners who offer crowdsourced data and data consumers who request data blocks negotiate with each other to make an agreement on data assignment and trading prices via a data trading platform; consequently, both sides gain profit from the process of data trading. A great many existing studies have investigated various kinds of data sharing or trading as well as protecting data privacy or constructing a decentralized data trading platform due to mistrust issues. However, existing studies neglect an important characteristic, i.e., dynamics of both data owners and data requests in trading crowdsourced data collected by IoT devices. To this end, we first construct an auction-based model to formulate the data trading process and then propose a near-optimal online data trading algorithm that not only resolves the problem of matching dynamic data owners and randomly generated data requests but also determines the data trading price of each data block. The proposed algorithm achieves several good properties, such as a constant competitive ratio for near-optimal social efficiency, incentive compatibility, and individual rationality of participants, via rigorous theoretical analysis and extensive simulations. We further design a decentralized data trading platform in order to construct a practical data trading process incorporating the proposed data trading algorithm.

Enabling Blockchain with IoMT Devices for Healthcare

Significant modifications have been seen in healthcare facilities over the past two decades. With the use of IoT-enabled devices, the monitoring and analysis of patient diagnostic parameters is made considerably easy. The new technology shift for medical field is IoMT. However, the problem of privacy for patient data and the security of information still a point to ponder. This research proposed a prototype model to integrate the blockchain and IoMT for providing better analysis of patient health factors. The authors suggested IoMT data to be collected over Edge Computing gateway devices and forward to Cloud Gateway. The three-layered decision making structure ensures the integrity of the data. The further analysis of information collected over sensor-based devices is done in the Cloud IoT Central Hub service. To ensure the secrecy and compliance of the patient data, Smart Contracts are integrated. After the exchange of smart contracts, a block of information is broadcast over the health blockchain. The P2P network makes it viable to retain all health statistics and further processing of information. The paper describes the scenario and experimental setup for a COVID-19 data-set analyzed in the proposed prototype mode. After the collection of information and decision making, the block of data is sent across all peer nodes. Thus, the power of IoMT and blockchain makes it easy for the healthcare worker to diagnose and handle patient data with privacy. The IoMT is integrated with artificial intelligence to enable decision making based on the classification of data. The results are saved as transactions in the blockchain hyperledger. This study demonstrates the prototype model with test data in a testing network with two peer nodes.

Using the spectral approach in image and arbitrary data processing

Introduction: The transfer of image processing operations to the spectral region is considered. Due to the duality of information representation, coding, filtering, compression and other transformations are possible both in the space of an object and in the region of spatial frequencies, in relation to its spatial spectrum. Purpose: To evaluate the efficiency of performing image processing operations and arbitrary digital information in the spectral domain. Results: A method for spectral holographic coding is proposed, which provides a gain in noise immunity by 7–8 dB and has less complexity of coding and decoding when changing redundancy over a wide range. During the coding process, the source data block is replaced by a code word, which is a linear one-dimensional hologram of a virtual point source. For transmission over a communication channel, we synthesize a signal with a given spectrum, the shape of which is a one-dimensional hologram, with its values rounded to one bit and the hologram itself being a sequence of zeros and ones – one means the presence of the corresponding harmonic in the spectrum, zero means the absence. To create a signal with such a line spectrum, it suffices to add a set of harmonics of equal amplitude with numbers corresponding to the position numbers of the units in the hologram. This operation is one of the types of orthogonal frequency division multiplexing, characterized in that the frequencies of the orthogonal subcarriers are in a multiple ratio, and amplitude shift keying is used as digital modulation. We propose a spectral method for image compression based on a detailed analysis of the spatial spectrum of an image and the removal of a large number of insignificant areas from it. Practical relevance: The reduction in the amount of information and, accordingly, the size of the image can be 4–8 times or more with a slight decrease in image quality.

Swiss knife covariates selection: A unified algorithm for covariates selection in single block, multiblock, multiway, multiway multiblock cases including multiple responses

AbstractA novel unified covariates selection algorithm called Swiss knife covariates selection (SKCovSel) is presented. It is suitable for selecting covariates in a wide range of data scenarios such as a single two‐way data block, two‐way multiblock, multiway, multiway multiblock, selection of covariates along different modes for multiway data blocks and for selecting covariates for all mentioned cases in multiple response scenarios. In the multiblock case, the method can be scale and data block order‐independent depending on the preference of the user. For multiway scenarios, the method can be multiway mode order independent, depending on the preference of the user. The proposed SKCovSel algorithm generalises the recent speed improvements from faster CovSel to all mentioned data block cases. It also reformulates the multiway case to do proper deflation and rank one slab selections. Particularly, for modelling of multiblock data sets, the SKCovSel follows the “winner takes all” strategy of the stepwise response‐oriented sequential alternation modelling. In the case of multiway data, the SKCovSel strategy considers multiway loading weights after decomposition of a high‐dimensional squared covariance matrix to select features across different modes. The algorithmic steps of the methods are presented, and cases of modelling different data types such as single block, multiblock, multiway multiblock, modes selection for multiway data and multiple responses modelling are shown. The method incorporates all popular covariates selection algorithms existing in the chemometric literature.

Automated Android Malware Detection Using User Feedback.

The widespread usage of mobile devices and their seamless adaptation to each user’s needs through useful applications (apps) makes them a prime target for malware developers. Malware is software built to harm the user, e.g., to access sensitive user data, such as banking details, or to hold data hostage and block user access. These apps are distributed in marketplaces that host millions and therefore have their forms of automated malware detection in place to deter malware developers and keep their app store (and reputation) trustworthy. Nevertheless, a non-negligible number of apps can bypass these detectors and remain available in the marketplace for any user to download and install on their device. Current malware detection strategies rely on using static or dynamic app extracted features (or a combination of both) to scale the detection and cover the growing number of apps submitted to the marketplace. In this paper, the main focus is on the apps that bypass the malware detectors and stay in the marketplace long enough to receive user feedback. This paper uses real-world data provided by an app store. The quantitative ratings and potential alert flags assigned to the apps by the users were used as features to train machine learning classifiers that successfully classify malware that evaded previous detection attempts. These results present reasonable accuracy and thus work to help to maintain a user-safe environment.

Aggregates of cationic calix[4]arenes in aqueous solution as media for governing protolytic equilibrium, fluorescence, and kinetics

Many water-soluble ionic calixarenes readily form micelle-like aggregates in aqueous solution. Presently, it is firmly proved that such aggregates tend to shift the state of the acid-base equilibrium of indicator dyes just in the same manner as cationic surfactant micelles do. In this paper, we further the corresponding studies and report the peculiarities of several kinds of solvatochromic effects, fluorescence, acid-base equilibrium and kinetic processes in aqueous solutions of four cationic amphiphilic calix[4]arenes bearing hydrophilic choline groups at the upper rim: 5,11,17,23-tetra(N,N-dimethyl-N-hydroxyethylammonium)methylene-25,26,27,28-tetraalkyl-oxycalix[4]arene tetrachlorides. n-Propyl, n-hexyl, n-octyl, and n-dodecyl were used as alkyls, and the calixarenes were designated as of Cn-C4A-Ch, where n = 3, 6, 8, and 12, respectively. The principal colloidal properties, i.e., particle size and electrophoretic mobility of aggregates were characterized via dynamic light scattering. In parallel, the results were compared with those obtained in the presence of micelles of the common cationic surfactant cetyltrimethylammonium bromide and of large-sized aggregates of the calix[6]arene with six methoxy groups at the lower rim. As tools, molecular probes of triphenylmethine and fluorescein series, as well as the solvatochromic Reichardt’s dye were used. The obtained block of data sheds light upon the properties of calixarene aggregates as tools for governing chemical processes.

An improved cross-subject spatial filter transfer method for SSVEP-based BCI

Objective. Steady-state visual evoked potential (SSVEP) training feature recognition algorithms utilize user training data to reduce the interference of spontaneous electroencephalogram activities on SSVEP response for improved recognition accuracy. The data collection process can be tedious, increasing the mental fatigue of users and also seriously affecting the practicality of SSVEP-based brain-computer interface (BCI) systems. Approach. As an alternative, a cross-subject spatial filter transfer (CSSFT) method to transfer an existing user data model with good SSVEP response to new user test data has been proposed. The CSSFT method uses superposition averages of data for multiple blocks of data as transfer data. However, the amplitude and pattern of brain signals are often significantly different across trials. The goal of this study was to improve superposition averaging for the CSSFT method and propose an Ensemble scheme based on ensemble learning, and an Expansion scheme based on matrix expansion. Main results. The feature recognition performance was compared for CSSFT and the proposed improved CSSFT method using two public datasets. The results demonstrated that the improved CSSFT method can significantly improve the recognition accuracy and information transmission rate of existing methods. Significance. This strategy avoids a tedious data collection process, and promotes the potential practical application of BCI systems.

Efficient mass spectrometric characterization and classification of methylmalonic aciduria subtypes through urinary and blood metabolic profiles fusion

Efficient subtype classification utilizing multiple biological information sources is clinically practical for precision treatment of inborn errors of metabolism (IEMs). This study utilized urinary GC–MS and dried blood spot MS/MS to enable complementary mass spectrometric characterization of pathological information for methylmalonic aciduria (MMA) subtypes. A novel mid-level data fusion strategy was subsequently described to effectively detect their subtle metabolic perturbations. In the proposed strategy, multivariate advantage was extracted via considering variable relationships in individual data blocks, separately. Further, it was extended to exploiting partial correlation across multiple data blocks, which induced the models between one data block and the first principal component (PC1) of another one for more valuable information recovery. The continuous values of PC1 replaced the traditional binary class labels, enabling suitable representation of disease heterogeneity numerically and subsequent accurate disease detection. Based on the unique role in exploratory data analysis, partial least squares discriminant analysis (PLS-DA) was coupled with bootstrap to form ensemble feature selection framework. It allowed the novel mid-level data fusion strategy to screen stable significant features. Investigated by two common MMA subtypes (mut and cblC) using urinary and blood metabolic profiles, the results showed that the novel mid-level data fusion strategy outperformed the traditional data fusion approaches both in predictive accuracy and biological interpretation. Besides, correlation network of the identified stable informative metabolites was visualized by chord plots, revealing different between-block biological interaction pattern for mut and cblC. Especially, in mut subtype, strong interactions could be occurred between the urinary metabolite of 3-OH-propionic-2 and two blood metabolite ratios (C3/C2 and C3/C0), separately. The findings deepened the biological insights into the disease pathology of mut and cblC. The integration of multiple analytical sources combined with the proposed novel mid-level data fusion strategy thus opened the possibilities to achieve desirable subtype classification for MMA. It suitably guided the early and timely medical intervention for IEMs.

CRP: Conditional Replacement Policy for Reliability Enhancement of STT-MRAM Caches

Driven by the trends of emerging technologies in on-chip memories, with increasing the size of last-level caches (LLCs), spin-transfer torque magnetic random access memories (STT-MRAMs) are the most promising alternative technology among the non-volatile memories (NVMs) to replace SRAMs. Despite their high density, scalability, and near-zero leakage power, the reliability of STT-MRAM LLCs is threatened by a high error rate due to their stochastic switching behavior. The error rate is highly influenced by the cache management, which necessitates redesigning the cache replacement policy based on the error behavior. In this article, we propose an error-aware cache replacement policy, namely, conditional replacement policy (CRP), to improve the reliability of STT-MRAM caches by decreasing the rate of both read disturbance and write failure. This is ascertained by nominating an appropriate data block in the cache to be replaced with an incoming data block, considering the minimum error rate. Moreover, the performance and latency of both write and read operations are considered. The simulation results show that compared with the state-of-the-art replacement policy in STT-MRAM caches, CRP reduces the total error rate by 68%. In addition, the proposed policy enhances the performance by 2% and saves energy consumption by 19%, on average. Meanwhile, the total number of writes is decreased by 41% compared with the previous scheme.

An Efficient Certificate-Based Data Integrity Auditing Protocol for Cloud-Assisted WBANs

With the evolution of wireless body area networks (WBANs), wearable equipment will improve the human healthcare service. However, the medical data generated in WBANs increase dramatically with time, and the massive data cause the storage burden. With the help of cloud computing, the cloud service provider (CSP) can assist data owners in storing these data collected by sensors. By keeping their data in the CSP, the data integrity and authenticity is a big concern of data owners. To date, many data integrity auditing protocols have been proposed to address this issue. Most of them rely on traditional public-key mechanism, or identity-based cryptography (IBC), or certificateless cryptography (CLC). However, they suffer from the heavy cost of certificate management, key escrow, or the requirement of a secret channel for each user, respectively. To solve these drawbacks, we propose an efficient certificate-based data integrity auditing protocol for cloud-assisted WBANs. In our protocol, the computation cost in tag generation for a data block is fixed, and is independent of the size of the data block. We prove our protocol is secure in the random oracle model (ROM) and use the Java pairing-based cryptography library (JPBC) to implement the protocol. The experimental results show that our protocol is computationally efficient and practical.

A new complexity reduction scheme in selective mapping‐based visible light communication direct current‐biased optical orthogonal frequency division multiplexing systems

Visible light communication (VLC) has emerged as a good accompaniment to radio-frequency (RF) technologies by deploying multicarrier schemes such as orthogonal frequency division multiplexing (OFDM). However, the coherent summation of carriers in the OFDM system leads to a high peak-to-average-power ratio (PAPR), causing non-linear clipping distortion at the transmitting light-emitting diode. This intricacy becomes a potential barrier for intensity modulation and limits the VLC systems' bandwidth. In the literature, non-distorting PAPR lowering approaches, such as the selective mapping (SLM) approach, have been confirmed as the most effective strategy for reducing ineludible high PAPR in optical OFDM systems among all other available techniques. Besides its astounding performance, the computational complexity also becomes a major complication in SLM due to the generation of multiple candidates. This paper proposes a computational complexity minimisation approach using inherit system properties in the SLM-based PAPR suppression method for VLC systems, where the phase sequence vectors are considered periodic. The alternative direct current-biased optical orthogonal frequency division multiplexing candidates for the single frequency-domain data block are generated with the periodic phase rotation vector. The evaluation of the complexity analysis and the simulation results shows that the mitigation of computational complexity surpasses the standard SLM technique.

Determination of heat flow and temperature variations for geothermal energy assessment over Sokoto Basin, Nigeria, using aero-magnetic and aero-radiometric data

The Nigerian sector of Iullemmeden Basin (Sokoto Basin and its adjacent region) contains sediments between the ages of Cretaceous and Tertiary covering the entire Basin. The area is bounded by latitude 12° 5ˈ – 14°00''N and longitude 4°00'' – 7°00''E. The study investigates geothermal energy resource potential over the Sokoto Basin using aeromagnetic and radiometric data. Seventeen (17) blocks of aeromagnetic and aero-radiometric data were gridded and processed using dimension of 55 km x 55 km. Spectral centroid method was employed to approximate depths to top and centroid of the magnetic sources of the study area. The results divulge that values of CPD range from 5.0 km to 12.5 km having a mean value of 8.8 km, whereby, the values of geothermal gradient range from 46.4 oCkm-1 to 116.9 oCkm-1 having a mean value of 81.6 oCkm-1, while the values of heat flow range from 115.9 mWm-2 to 292.1 mWm-2 having a mean value of 204.1 mWm-2. The study also reveals that, the values of radiogenic heat range between 0.81 and 2.87 μWm-3. The zones having high concentration of thorium and uranium trending N-S and S-W extend to Niger Republic across mid-northern border. The result from this study also reveals that, Curie temperature could be attained at the depth of 6 km deep. Conclusively, those spots having shallow CPD and high heat flow may be potential for geothermal energy source.

Joint message-passing-based accurate bidirectional channel estimation and generalized-approximation-message-passing-based low-complexity perfect equalization with underwater moving transceivers

Moving underwater acoustic communications incur the fast time-varying multipath interference (FTMI), leading to a decrease in decoding performance or even decoding failure. In this study, we address the FTMI issue using the superimposed training (ST) scheme and segment strategy with a joint channel estimation and equalization algorithm. The ST scheme refers to the linear superposition of the training sequence with a small power to the symbol sequence; the segment strategy slices a data block into the segments. Thus, the tracking capability of time-varying channels is significantly improved. To realize their full potential, a “novel” joint message-passing-based accurate bidirectional channel estimation and generalized-approximation-message-passing-based low-complexity perfect equalization (BCE-LPE) algorithm is developed. The Gaussian channel estimates of the segments can be parameterized by their means and variances, thereby enabling fusion of the channel estimates. The correlation of the channel estimates for the segments is established through a channel correlation coefficient, so that the whole data block can be used to estimate the channel of each segment, leading to an accurate channel estimation. Unlike the Gaussian approximate process of the input symbol sequence of the traditional linear equalization, the proposed low-complexity perfect equalization maintains the discrete and independent form of the input symbol sequence, avoiding the equalizer’s input information loss. The a priori, a posteriori, extrinsic means and variances of interleaved encoded bits are computed using the low-complexity diagonal-matrix message passing, leading to the low-complexity perfect equalization, with computational complexity in a logarithmic order per symbol. Moreover, channel estimation, equalization, and decoding are jointly performed in an iterative manner to significantly enhance the overall system performance. Additionally, the parallel processing strategy is used to improve the computation speed, in which all the data blocks are separately and parallelly processed. Field experiments with moving transceivers (the communication distance was about 5.5 km, the bandwidth was 4 kHz, and the transmission rate was 3765 bits/s) were performed in Jiaozhou Bay in 2021, with the experimental results verifying the effectiveness of the BCE-LPE algorithm.