Repetitive Operation Research Articles

Features of the impact of digitalization of accounting on the business processes of enterprises

The article examines the trend in the development of services and the provision of qualified electronic signatures and electronic seals for use by business entities, including those that use registrars of settlement transactions. It was determined that the development of digital methods of processing and receiving information by state bodies leads to the need for the mandatory use of digital technologies by business entities, which ultimately requires appropriate methodological support for the implementation of such changes in the field of the document flow of accounting, statistical and tax documents since certain reporting forms following tax legislation are sent to tax authorities exclusively in electronic form. The understanding of the concept of mandatory details of an electronic document, as well as its definition in the main legislative acts that are used by state bodies and to which the business entity submits financial, statistical and other types of reporting in electronic format, is analyzed. The main organizational advantages of conducting digital accounting due to the use of cloud technologies for storing information and electronic data on transactions carried out among counterparties for their further use in repetitive operations are presented, i.e., the creation of a modern working environment for further digital accounting and reporting, which ensures its functionality and physical security employees, economy and information flexibility. Organizational approaches to the system of digital accounting with the help of automated data collection and storage in cloud data warehouses for the formation of primary documents and reporting in real-time in terms of counterparties and standardized reporting forms are considered. It has been established that the development of digital accounting is a consistent trend of changing the state's approaches to interaction with business and is also directly related to the development of information technologies, and is an inevitable change to traditional paper approaches in the conditions of digital transformation of the world economy.

Application of automatic driving task serialisation monitoring for operating robots

Abstract With the increasing application of industrial robots, more and more simple and repetitive operations in industrial automated production lines are replaced by industrial robots. In this study, a path planning algorithm is proposed for the autopilot task of an operating robot to find the optimal path from the start point to the goal point under the constraints of safe obstacle avoidance, shortest distance, and fastest time. Forward kinematics is used to detect whether it will collide with environmental obstacles until the first feasible result is detected as the end position for navigation. Serialized monitoring is used to obtain the activity information of each computational node, the hardware state information of the system, and the state of the autopilot task processing. Finally, obstacle avoidance navigation experiments on a mobile operating robot are conducted to verify the effectiveness and feasibility of the obstacle avoidance navigation algorithm. The results show that the maximum error of the autopilot task of the operating robot is 2.91cm, and the average error is 0.13 2cm, which is in line with the trajectory tracking error requirements of the operating machine control method and verifies the validity and practicability of this study.

Model Free Adaptive Iterative Learning Control Based Fault-Tolerant Control for Subway Train With Speed Sensor Fault and Over-Speed Protection

A model free adaptive iterative learning control based fault-tolerant control (MFAILC-FTC) scheme for subway train speed tracking with speed sensor fault and over-speed protection is proposed. Firstly, the train dynamics is transformed into a compact form dynamic linearization (CFDL) data model by applying the concept of pseudo-partial derivative (PPD). If speed sensor fault occurs, the fault function is approximated by the trained RBFNNs under normal condition and the output data of the train system with fault, which serves as a compensation for the proposed MFAILC-FTC scheme. Then, over-speed protection mechanism is developed to ensure that the train operates within safe speed range. Furthermore, the constraint on traction/braking force is also taken into account. Through rigorous mathematical analysis, it is proved that the proposed MFAILC-FTC method with over-speed protection mechanism can ensure the train speed tracking error converges along the iteration axis, which implies the train operates safely and reliably. Finally, the simulation results further demonstrate the effectiveness of the proposed algorithm. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Subway train as a practical engineering system with short distance between two stations, starts and stops frequently, has the outstanding repetitive operation pattern, and it is unavoidable subject to speed sensor fault, aerodynamic issues, constraint on output speed and traction/braking force. Nevertheless, few works have considered these factors simultaneously, and a lot of data contain valuable operation information are generated during the train operation, this motives the work of this note. On account of the repetitive operation features of subway trains, the control schemes of speed trajectory tracking are handled under MFAILC framework, which is a pure data-driven model free control methodology. By constructing the RBFNNs-based fault function estimation mechanism, a robust compensation term is designed in the fault-tolerant controller. Taking the safe operation of subway trains into account, an over-speed protection term with trigger mechanism is added to the fault-tolerant controller. To further enhance the application, the constraint on traction/braking force is addressed as well. Without requirement of the train dynamics model, the theoretical analyses and simulation results have confirmed the effectiveness and the feasibility of the proposed data-driven control approach. In the future work, we will focus on verifying the proposed control strategy and addressing some other practical problems, for instance, the energy-efficiency and exogenous disturbances during the train operation.

Optimal Injection Attack Strategy for Nonlinear Cyber-Physical Systems Based on Iterative Learning

This paper aims to investigate the security problem of nonlinear cyber-physical systems (CPSs), which poses a challenge to handle compared with linear CPSs. A series of optimization problems for nonlinear CPSs under injection attack are constructed, which are based on a general model of the nonlinear systems with repetitive operation characteristics and a novel introduction of the key technical lemma. These optimization results are more general than the existing injection attack results and the requirements for attackers to obtain system information are relaxed. Also, the form of switching applied to the attack strategy possesses several advantages, including high stealthiness, lower cost, and more flexibility. Therefore, the new optimal injection attack strategies are expected to be more widespread and provide a basis for the design of defense strategies. The key to acquiring the designed optimal attack strategies is to adopt the linear input/output (I/O) data model for these systems via introducing an estimation term of the improved projection estimation method into the linear model. Finally, a networked GLUON-6L3 manipulator example validates the effectiveness of the proposed methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The main purpose of this paper is to study the cyber security of nonlinear cyber-physical systems from the perspective of attackers, which can help defenders fully understand the behavior of attackers. Most of the existing attack strategies aimed at linear systems or have a priori knowledge of the attacked systems. However, there are great limitations and difficulties in practical application. In this paper, the new attack strategies are proposed by combining system identification, iterative learning and control theory, which relaxes the requirement of the attacker’s ability. In detail, the attacker only needs to obtain the control input and output data of the attacked system and design the attack strategy according to it. Among them, the first-in, first-out queue storage method is applied to remove the requirements for the storage capability of the attacker. In practical applications, the attacker does not need to store the I/O data continuously, but only store the initial value and the data of two successive iterations. The mathematical analytic forms of two optimal attack strategies are given, and then their effectiveness are verified on a welding work of a networked six-axis manipulator. In the future, we will investigate the design of attack strategies for nonlinear systems with heterogeneous dynamics and multiple delays.

Lightweight Computational Complexity Stepping Up the NTRU Post-Quantum Algorithm Using Parallel Computing

The Nth-degree Truncated polynomial Ring Unit (NTRU) is one of the famous post-quantum cryptographic algorithms. Researchers consider NTRU to be the most important parameterized family of lattice-based public key cryptosystems that has been established to the IEEE P1363 standards. Lattice-based protocols necessitate operations on large vectors, which makes parallel computing one of the appropriate solutions to speed it up. NTRUEncrypt operations contain a large amount of data that requires many repetitive arithmetic operations. These operations make it a strong candidate to take advantage of the high degree of parallelism. The main costly operation that is repeated in all NTRU algorithm steps is polynomial multiplication. In this work, a Parallel Post-Quantum NTRUEncrypt algorithm called PPQNTRUEncrypt is proposed. This algorithm exploits the capabilities of parallel computing to accelerate the NTRUEncrypt algorithm. Both analytical and Apache Spark simulation models are used. The proposed algorithm enhanced the NTRUEncrypt algorithm by approximately 49.5%, 74.5%, 87.6%, 92.5%, 93.4%, and 94.5%, assuming that the number of processing elements is 2, 4, 8, 12, 16, and 20 respectively.

A STUDY OF RAPID MAPPING TECHNOLOGY BASED ON ADOBE ILLUSTRATOR

Abstract. At present, China's urban and rural construction, national security, emergency and disaster relief have put forward higher and faster requirements for high-quality and current maps. How to use the latest spatial database in the shortest possible time to produce and provide high-quality, highly presentable, content-rich maps is an urgent issue. In this paper, we study the rapid mapping technology based on GIS platform and map mapping software, study the automatic map mapping method under AI environment, design and develop the spatial basic geographic database-driven rapid mapping system, realize the automatic lossless conversion of GIS data to map mapping software according to the established mapping rule base, realize the automatic configuration of symbols and annotations, and realize the automation of processing of element relationship. The AI-based database-driven rapid mapping technology has been used in the practice of map compilation in prefecture-level cities, replacing most of the manual repetitive operations, greatly improving the efficiency of map compilation, and enhancing the capacity of emergency mapping services.

Fluoranthene biotreatment using prominent freshwater microalgae: physiological responses of microalgae and artificial neural network modeling of the bioremoval process

Due to the intensified industrial activities and other anthropogenic actions, contamination of polycyclic aromatic hydrocarbons (PAHs) has been growing at an alarming rate, turning in to a serious environmental concern. Bioremediation, as an eco-friendly and sustainable removal technology, can be used by organisms to reduce the resulting contaminations. In the present study, the ability of Tetradesmus obliquus to remove of fluoranthene (FLA) was evaluated. It was confirmed that FLA removal efficiency was managed by various environmental parameters and pH was found to be one of the most important influencial factors. The reusability of the algae in long-term repetitive operations confirmed the occurrence of biodegradation along with other natural attenuation and 10 intermediate compounds were identified in the FLA biodegradation pathway by GC-MS. As a result of physiological assays, induced antioxidant enzymes activities and augmentation of phenol and flavonoids contents, after the treatment of the microalgae by a high concentration of FLA, confirmed the ability of the microalgae to upregulate its antioxidant defense system in response to the toxic effects of FLA. An artificial neural network (ANN) model was then developed to predict FLA biodegradation efficiency and the appropriate predictive performance of ANN was confirmed by comparing the experimental FLA removal efficiency with its predicted amounts (R2 = 0.99).

Ultrafast (∼0.6 s), Robust, and Highly Linear Hydrogen Detection up to 10% Using Fully Suspended Pure Pd Nanowire.

The high explosiveness of hydrogen gas in the air necessitates prompt detection in settings where hydrogen is used. For this reason, hydrogen sensors are required to offer rapid detection and possess superior sensing characteristics in terms of measurement range, linearity, selectivity, lifetime, and environment insensitivity according to the publicized protocol. However, previous approaches have only partially achieved the standardized requirements and have been limited in their capability to develop reliable materials for spatially accessible systems. Here, an electrical hydrogen sensor with an ultrafast response (∼0.6 s) satisfying all demands for hydrogen detection is demonstrated. Tailoring structural engineering based on the reaction kinetics of hydrogen and palladium, an optimized heating architecture that thermally activates fully suspended palladium (Pd) nanowires at a uniform temperature is designed. The developed Pd nanostructure, at a designated temperature distribution, rapidly reacts with hydrogen, enabling a hysteresis-free response from 0.1% to 10% and durable characteristics in mechanical shock and repetitive operation (>10,000 cycles). Moreover, the device selectively detects hydrogen without performance degradation in humid or carbon-based interfering gas circumstances. Finally, to verify spatial accessibility, the wireless hydrogen detection system has been demonstrated, detecting and reporting hydrogen leakage in real-time within just 1 s.

A Physical Fatigue Evaluation Method for Automotive Manual Assembly: An Experiment of Cerebral Oxygenation with ARE Platform

Due to the complexity of the automobile manufacturing process, some flexible and delicate assembly work relies on manual operations. However, high-frequency and high-load repetitive operations make assembly workers prone to physical fatigue. This study proposes a method for evaluating human physical fatigue for the manual assembly of automobiles with methods: NIOSH (National Institute for Occupational Safety and Health), OWAS (Ovako Working Posture Analysis System) and RULA (Rapid Upper Limb Assessment). The cerebral oxygenation signal is selected as an objective physiological index reflecting the human fatigue level to verify the proposed physical fatigue evaluation method. Taking auto seat assembly and automobile manual assembly as an example, 18 group experiments were carried out with the ARE platform (Augmented Reality-based Ergonomic Platform). Furthermore, predictions of metabolic energy expenditure were performed for experiments in Tecnomatix Jack. Finally, it is concluded that the proposed physical fatigue evaluation method can reflect the human physical fatigue level and is more accurate than the evaluation of metabolic energy consumption in Tecnomatix Jack because of the immersion that comes with the AR devices and the precision that comes with motion capture devices.

A Programmable Crypto-Processor for National Institute of Standards and Technology Post-Quantum Cryptography Standardization Based on the RISC-V Architecture

The advancement of quantum computing threatens the security of conventional public-key cryptosystems. Post-quantum cryptography (PQC) was introduced to ensure data confidentiality in communication channels, and various algorithms are being developed. The National Institute of Standards and Technology (NIST) has initiated PQC standardization, and the selected algorithms for standardization and round 4 candidates were announced in 2022. Due to the large memory footprint and highly repetitive operations, there have been numerous attempts to accelerate PQC on both hardware and software. This paper introduces the RISC-V instruction set extension for NIST PQC standard algorithms and round 4 candidates. The proposed programmable crypto-processor can support a wide range of PQC algorithms with the extended RISC-V instruction set and demonstrates significant reductions in code size, the number of executed instructions, and execution cycle counts of target operations in PQC algorithms of up to 79%, 92%, and 87%, respectively, compared to RV64IM with optimization level 3 (-O3) in the GNU toolchain.

Novel dynamic method based on CV-SECM and SWV-SECM for the in situ chemical imaging of reactive metal surfaces undergoing corrosion and corrosion inhibition illustrated with the case of copper corrosion inhibition by benzotriazole

A novel dynamic method for the chemical imaging of actively corroding metal surfaces using scanning electrochemical microscopy (SECM) is proposed by using CV-SECM and SWV-SECM. This consists of an adequate coupling of a repetitive voltammetric operation at the SECM tip while conducting the rastering routine for scanning a reactive copper surface, as well as its inhibition by benzotriazole. In this method, gold microelectrodes are employed as SECM tips, and therefore their electrochemical behaviour towards collection and redissolution of Cu2+ ions from synthetic solutions containing Cu2+ ions. Next, the dynamic application of voltammetric methods for the collection and stripping of copper on the Au probes while mapping copper surfaces was investigated. The proof of concept first involved continuous cyclic voltammetry (CV-SECM) in an acidified NaCl solution, in terms of Cu2+ dissolution and surface redox activity (with SECM in the feedback mode). Then, square wave voltammetry (SWV-SECM) was used to detect small copper dissolution from corroding and inhibitor-protected metal surfaces. The results are consistent with a heterogeneous nature of copper degradation and the development of protective films and passive layers.

Prevalence and risk factors of work-related musculoskeletal disorders among emerging manufacturing workers in Beijing, China.

The workers in emerging manufacturing are at decreased risk of traditional occupational diseases, while probably at increased risk of work-related musculoskeletal disorders (WMSDs). This study aimed to investigate the prevalence and risk factors of WMSDs among emerging manufacturing workers in Beijing. A total of 3,359 valid questionnaires were collected from 10 enterprises in the electronics, pharmaceutical, and motor manufacturing industries. The prevalence of WMSDs was assessed using the Nordic Musculoskeletal Questionnaire. The work posture load was evaluated through a questionnaire. The results showed that the highest prevalence of WMSDs was observed in part of the neck (15.0%), followed by the lower back (12.5%), shoulders (11.2%), and upper back (7.1%). Female workers, workers aged older than 35 years, workers with a BMI of ≥28 kg/m2, longer working experience, never exercised had a higher prevalence of WMSDs. Logistic regression analysis showed that female workers, workers aged older than 35 years, with a middle school education and college degree, and workers who never exercised had a higher risk of WMSDs. In addition, workers who sat for long during work, worked hard with upper limbs or hands, worked in uncomfortable postures, and performed repetitive operations were positively related with the increased risk of WMSDs. These findings suggested that WMSDs were prevalent among emerging manufacturing workers in Beijing, China, while efforts should be made to reshape the risk factors associated with WMSDs, such as prolonged sitting, uncomfortable positions, and repetitive operations. Encouraging exercise and promoting ergonomic interventions probably be also benefit to induce the risk of WMSDs.

Remote dismantling system using a digital manufacturing system and workpiece localization for nuclear facility decommissioning

A remote dismantling system using a semi-automated robotic system is presented for enhanced efficiency and protection against worker exposure in nuclear facility decommissioning. In the conventional nuclear facility decommissioning, application of an automated robotic system has been difficult due to radiation and harsh environments, so simple and repetitive remote dismantling operations involving field workers has been necessary. In this paper, a digital manufacturing system and workpiece localization are applied to realize a semi-automated remote dismantling system. The digital manufacturing system and workpiece localization enable robot path planning in a virtual environment and robot path correction for a field workpiece without requiring field workers to teach the robot. This paper presents a control framework for the remote dismantling system and methodologies for building a digital model that represent the robot system applied to an actual workshop and localizing the workpiece through 3D registration. Various experimental results using a robot system of actual size and a target structure similar to reactor internals in shape and material demonstrate the successful achievement of the presented remote dismantling system. The proposed control framework and methodologies are expected to contribute to the automation of simple repetitive dismantling operations and to reduce worker exposure.

FASER: Fault-affected signal energy ratio for fault diagnosis of gearboxes under repetitive operating conditions

Vibration signal analysis is crucial for gearbox fault diagnosis, yet its inherent stochastic nature can challenge the identification of fault-induced changes amidst signal variability. This paper introduces a novel fault diagnosis approach, the Fault-Affected Signal Energy Ratio (FASER), designed to account for the uncertainty in vibration signals under repetitive operating conditions. The uncertainty is quantified using probability distributions of coefficients derived from Short-Time Fourier Transform (STFT) applied to normal state signals, employing Kernel Density Estimation and Kullback-Leibler divergence. This combined approach enables the quantification of uncertainty in signals with non-constant uncertainty, dependent on time and frequency, when converted to STFT. These distributions facilitate the assessment of the FASER in new signals extracted under synchronized operating conditions using our proposed method. This newly proposed FASER, accompanied by adaptive threshold to address feature randomness from STFT indices’ correlation, serves as a robust health indicator. Experimental validation demonstrates the effectiveness of the proposed method in accurate gearbox fault diagnosis under repetitive operating conditions, along with the capability to estimate fault severity levels.

Data-Driven Spatial Adaptive Terminal Iterative Learning Predictive Control for Automatic Stop Control of Subway Train With Actuator Saturation

A data-driven spatial adaptive terminal iterative learning predictive control (SATILPC) scheme with actuator saturation is proposed for automatic stop control of the subway train. Considering the outstanding repetitive operation pattern and the unavailable accurate model of a subway train, the unknown train dynamics is firstly transformed into a nonlinear discrete form in spatial domain via the spatial differential operator. Since the train automatic stop control (TASC) only concentrates on the tracking performances of the terminal position and terminal speed, an iterative dynamic linearization approach considering the terminal operation point is devised to formulate the relationship of the train input and output (I/O) into a linear affine form. Then, a terminal iterative learning prediction mechanism is introduced to reconstruct the developed train data model to forecast the future train behaviors through rolling optimization process. As a result, by removing the constraints on the unimportant points, the optimal control input (braking force) can be obtained by minimizing the objective function through terminal I/O data. Further, actuator saturation is considered to address the passenger comfort and the reliable operation of the train. The proposed SATILPC approach is a pure data-driven iterative learning control scheme and no model information is involved in the whole design processes. By utilizing a newly space-based contraction mapping method, the convergence of the proposed approach is strictly proved. Finally, the simulation results further demonstrate the feasibility of the proposed algorithm.

The Impact of Artificial Intelligence on Human Workers

The impact of artificial intelligence on human workers is a complex and ongoing topic of research and debate, and the extent to which AI will replace human jobs is still uncertain. Therefore, this research aims to answer following research questions. How does artificial intelligence affect human workers? What jobs will be replaced by artificial intelligence? What jobs can endure without being replaced by artificial intelligence?. This research was conducted in qualitative approach based on secondary data from previous studies. Data analysis techniques through four stages, namely data collection, data reduction, data presentation and drawing conclusions. After reviewing the remaining articles for eligibility in terms of the inclusion criteria, 45 papers were included in the data analysis. This study conclude that artificial intelligence has the ability to augment human talents, generate innovation, offer new career possibilities, and improve decision-making. Adopting AI technologies not only improves employee skills and productivity, but also enables organizations to function more efficiently. This study found that the negative effects of AI, such as job displacement, lower labour demand, employee deskilling, erosion of privacy and autonomy, exacerbation of wealth inequality, and shifting employee requirements. AI has the potential to disrupt traditional work functions in routine and repetitive tasks, manual labour, high-paying occupations, decision-making roles, HR operations, and certain service industry jobs. AI struggles to imitate creative endeavours, emotional intelligence, physical dexterity, human interaction, and complicated decision-making. These professions will continue to thrive as technology advances, reminding us that the essence of human experience is irreplaceable.

Improving End-Point Position Control in Hydraulic Testing Machines with a Fuzzy Logic Based Approach

During the repetitive operation of hydraulic testing machines, some undesirable vibration movements and non-compliance with the set value may occur at the piston end-point, which is the output of the system. PID (Proportional-Integral-Derivative) control is widely used in such systems in practical applications. However, the use of a standard (fixed coefficient) PID control alone cannot completely eliminate problems such as endpoint vibration and/or non-compliance of the endpoint position with the set value, caused by dynamic parameter changes in the hydraulic system. In the current state of the applications, when such a situation is encountered, the controller coefficients need to be readjusted by a human operator. In this study, to avoid this need and automatically adjust PID controller coefficients, a fuzzy logic-based computation approach has been developed and applied to the existing control system. A hydraulic system was designed and realized to test the developed method. The end-point position control of the system was established and improved utilizing the developed approach. With this development, an improvement of more than 10% was achieved in the adjustment of the hydraulic testing machine end-point oscillation amplitude to the set value. The use of this method also eliminates the need for human operators to readjust the controller parameters in case of long-term operation of hydraulic test systems.

Influence of Diameter and Cyclic Mechanical Stimulation on the Beating Frequency of Myocardial Cell-Laden Fibers.

Atrioventricular block (AVB) is a severe disease for pediatric patients. The repetitive operations needed in the case of the pacemaker implantation to maintain the electrical signal at the atrioventricular node (AVN) affect the patient's life quality. In this study, we present a method of biofabrication of multi-cell-laden cylindrical fibrin-based fibers that can restore the electrical signal at the AVN. We used human umbilical vein smooth muscle cells (HUVSMCs), human umbilical vein endothelial cells (HUVECs) and induced pluripotent stem cell cardiomyocytes (iPSC-CMs) cultivated either statically or dynamically to mimic the native AVN. We investigated the influence of cell composition, construct diameter and cyclic stretch on the function of the fibrin hydrogels in vitro. Immunohistochemistry analyses showed the maturity of the iPSC-CMs in the constructs through the expression of sarcomeric alpha actinin (SAA) and electrical coupling through Connexin 43 (Cx43) signal. Simultaneously, the beating frequency of the fibrin hydrogels was higher and easy to maintain whereas the concentration of iPSC-CMs was higher compared with the other types of cylindrical constructs. In total, our study highlights that the combination of fibrin with the cell mixture and geometry is offering a feasible biofabrication method for tissue engineering approaches for the treatment of AVB.

A Multi-Scale Context Aware Attention Model for Medical Image Segmentation.

Medical image segmentation is critical for efficient diagnosis of diseases and treatment planning. In recent years, convolutional neural networks (CNN)-based methods, particularly U-Net and its variants, have achieved remarkable results on medical image segmentation tasks. However, they do not always work consistently on images with complex structures and large variations in regions of interest (ROI). This could be due to the fixed geometric structure of the receptive fields used for feature extraction and repetitive down-sampling operations that lead to information loss. To overcome these problems, the standard U-Net architecture is modified in this work by replacing the convolution block with a dilated convolution block to extract multi-scale context features with varying sizes of receptive fields, and adding a dilated inception block between the encoder and decoder paths to alleviate the problem of information recession and the semantic gap between features. Furthermore, the input of each dilated convolution block is added to the output through a squeeze and excitation unit, which alleviates the vanishing gradient problem and improves overall feature representation by re-weighting the channel-wise feature responses. The original inception block is modified by reducing the size of the spatial filter and introducing dilated convolution to obtain a larger receptive field. The proposed network was validated on three challenging medical image segmentation tasks with varying size ROIs: lung segmentation on chest X-ray (CXR) images, skin lesion segmentation on dermoscopy images and nucleus segmentation on microscopy cell images. Improved performance compared to state-of-the-art techniques demonstrates the effectiveness and generalisability of the proposed Dilated Convolution and Inception blocks-based U-Net (DCI-UNet).

Faster TKD: Towards Lightweight Decomposition for Large-Scale Tensors With Randomized Block Sampling

The Tucker Decomposition (TKD) is able to provide the low-dimensional and informative representations of real-world large-scale tensorial data, which are necessary to extract potential features and enhance the original data. However, computing such decomposition directly for a dense tensor is usually computationally elusive, due to the repetitive operations of computing large-scale tensor-matrix product. Instead of direct decomposition, this paper proposes an efficient algorithm for seeking the Faster TKD of the large-scale tensor, which is a lightweight decomposition approach based on the technique of randomized sampling. The proposed algorithm first converts the original large-scale tensor into a small-scale subtensor via full-mode sampling operation, and then the core tensor of TKD can be computed directly based on the subtensor with low complexity. Finally, an approximate TKD of the original large-scale tensor can be obtained after sequentially computing approximate full-mode factor matrices. A theoretical error analysis is provided to show that the approximation error approximates zero with high probability, and the proposed algorithm is verified based on real tensorial data of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{23821.24}~GB$</tex-math></inline-formula> .