Data Processing Speed Research Articles

Recognizing fake news based on natural language processing using the BM25 algorithm with fine-tuned parameters

The object of the research is the method of natural language processing (NLP) with balanced parameters of the BestMatch25 (ВМ25) algorithm to recognize and classify fake news based on natural language processing (NLP). The unsatisfactory accuracy and speed of existing methods for detecting fake news in unstructured input data demanded the development of a new approach for their effective detection. The study investigated the BM25 algorithm, methods for selecting parameters k1 and b, and their impact on the algorithm's effectiveness in detecting fake news. It was established that precise and detailed adjustment of these parameters is crucial in achieving optimal accuracy and data processing speed. The results showed that the successful selection of BM25 parameters improves the model's accuracy by up to 14 % compared to standard term frequency – inverse document frequency (TF-IDF) calculations. These results were made possible by experimentally tuning different combinations of k1 and b parameters, in which the algorithm shows the best speed indicator or the most accurate estimate of the importance of a term in a document. Balanced values of k1 and b parameters were identified, leading to the algorithm's optimal speed and accuracy in assessing word importance considering the input data's peculiarities. The balanced setting of the BM25 algorithm parameters explains the obtained results. They can be used for automated recognition and analysis of news and information on social media based on natural language processing. However, in practice, the effectiveness of the set of parameters depends on linguistic variations, content, and the theme within new input data sets

The growing use and impact of artificial intelligence technologies in the tourism industry

The research relevance is determined by the increasing role of artificial intelligence in the tourism business, which was demonstrated during the outbreak of the COVID-19 pandemic in Bali, resulting in a decline in the number of tourists visiting the island. The research aims to investigate the real-life experience of applying artificial intelligence systems in the tourism industry to address the challenges of developing the tourism industry in Bali, Indonesia. The basis of the methodological approach is a combination of theoretical methods of analysis and synthesis of the collected information covering the practical experience of the application of artificial intelligence systems in the tourism industry, as well as a survey of customers of travel agencies that have used such systems in trips to Bali. The research results show that artificial intelligence can significantly help the tourism business in Bali, as the number of tourists visiting the island dropped by 40% during the pandemic, resulting in a reduction in the number of tourism staff. The practical application of systems based on artificial intelligence opens up a wide range of business opportunities, as it allows for optimizing the activities of tourism firms and providing customers with high-quality services with highly technical equipment. The use of neural network mathematical models of tourist firms’ activity based on AI, allows them to achieve high speed of data processing, which allows tourist firms numerous competitive advantages and significantly improves the quality of their services. The practical significance of the results of this scientific research lies in the possibility of their application in the organization of the activities of enterprises in the sphere of tourism business, built on the use of digital technologies and systems based on artificial intelligence.

The Advantages and Challenges Faced by Business Analytics in the Context of Big Data

In recent years, with the booming development of big data technology, data acquisition and data analysis have become more convenient and efficient, and business data analysis is gradually being widely used in various industries. This paper analyses how business analytics can seize the opportunities for better development in the era of big data, and also explains the challenges faced by business analytics in the era of big data and provides corresponding solutions. The article finds that big data can help business analytics better predict market trends, optimise marketing strategies, provide visual analysis reports, and detect fraud risks; at the same time, the problems of data quality, data security, data processing speed, and data processing capacity arise; finally, the article puts forward ways to solve these problems from the perspectives of improving the quality of data, improving the level of protection, improving the speed of processing, and improving the capacity of analytics, which provides diversified ideas for people.

Comparing the RSA and elgamal encryption methods

In the realm of computer science, the speed and efficiency of data processing vary depending on the chosen algorithms and programming languages. This article delves into an exploration of which combinations can yield the highest overall performance. Starting with an introduction to the selected algorithms and languages, the underlying mathematical foundations and principles of each algorithm are presented. The research then shifts its focus to the practical aspect translating these algorithms into executable code. Three specific combinations are tested: RSA algorithm implemented in Python, Elgamal algorithm implemented in Python, and RSA algorithm executed in C++. To ensure reliable results, each combination underwent 30 test iterations, with empirical data subsequently gathered. Two primary comparisons were conducted: the first pitting the Python-based RSA against the Python-based Elgamal, and the second contrasting the Python-based RSA with its C++ counterpart. From these tests, a compelling conclusion emerges. When it comes to transmitting encrypted messages and subsequently decrypting them, the RSA algorithm paired with Python emerges as the most optimal choice. Readers will gain a deeper understanding of the strengths and potential limitations of each pairing, equipping them to make more informed decisions in their cryptographic endeavors.

Towards “smart transceivers” in FPGA-controlled lithium-niobate-on-insulator integrated circuits for edge computing applications [Invited

In the realm of advanced computing and signal processing, the need for optimized data processing methodologies is steadily increasing. With the world producing vast quantities of data, computing architectures necessitate to be swifter and more energy efficient. Edge computing architectures such as the NetCast architecture [1] combine the strength of electronic and photonic computing by outsourcing multiply-accumulate operations (MAC) to the optical domain. Herein we demonstrate a hybrid architecture, combining the advantages of FPGA data processing facilitating an ultra-low power electro-optical “smart transceiver” comprised of a lithium-niobate on insulator photonic circuit. The as-demonstrated device combines potential GHz speed data processing, with a power consumption in the order of 6.63 fJ per bit. Our device provides a blueprint of a unit cell for a TFLN smart transceiver alongside a variety of optical computing architectures, such as optical neural networks, as it provides a low power, reconfigurable memory unit.

Simulation of supersonic jet flow past a blunt body in a laboratory experiment using computer vision

The complex flow of a supersonic jet (Mach number 2.4–2.5) around the blunt aerodynamic body (consisting of a cylinder with a diameter of 16 mm and a truncated cone) was studied using the high-speed shadowgraph technique and computer vision-based visual data processing. The problem considered is directly related to the rocket and space systems stages safe separation problem in a sufficiently dense atmosphere. For systems with a sequential arrangement of stages, their separation often occurs under the rocket engine jet action. The occurrence of lateral forces in violation of axial symmetry can lead to overturning of the discarded stage and undesirable interaction with the outgoing stage. The goals of the paper were to study the pulsation characteristics of the incoming supersonic jet streamlining the body, as well as the pulsations of the bow shock wave in both axisymmetric and asymmetric flows. The recording frame rate in the experiments was up to 775 000 fps. Computer vision and various machine learning approaches were used to process a large number of shadowgraph images. Canny edge detection and Hough transform, as well as a convolutional neural network (CNN) based on YOLOv2 architecture, were used to automatically track the position of the bow shock relative to the body. Jet sound generation was studied - the amplitude dependence on the distance from the nozzle and the evolution in time. The position of the bow shock relative to the streamlined body and flow pulsations over time were analyzed. Bow shock pulsation spectra at zero angle of attack were compared to those at a small angle of attack (α = 2.5°–3°). The power spectral density was also estimated. The slope of the spectra for the zero angle of attack case was found to be horizontal and the spectra for the small angle of attack case had a slope close to −5/3. The strongest of the measured bow shock frequencies were found to be close to those of the jet mixing layer pulsations. The hardware signal spectrum was also measured and this signal can be considered as noise. The described approach makes it possible to obtain the physical characteristics of the flow at any point of interest. It was also shown that the automation of flow visualization experiments using computer vision techniques allows to increase the speed of data processing and obtaining new physical information, which may be important for engineers developing aircraft and spacecraft technologies.

Application of Big Data Privacy Protection Based on Edge Computing in the Prediction of Martial Arts Training Movement Trajectory

With the development of science and technology, edge computing and big data privacy protection are more and more widely used in various fields. The application of big data privacy protection based on edge computing in the prediction of sport trajectories for martial arts training shows good performance and privacy protection. Edge computing can process and analyze data in real time to improve the accuracy and efficiency of sport trajectory prediction. Big data privacy protection can ensure the security of athletes' personal information and training data and prevent data leakage and misuse. However, existing related works still have some deficiencies in data processing speed, accuracy, and privacy protection. In this paper, the authors address these issues and propose an edge computing-based big data privacy protection method to improve the accuracy and security of sport trajectory prediction for martial arts training.

Log specification and intelligent analysis method based on oil and gas pipeline SCADA system

Abstract As the control center of the natural gas long-distance pipeline network, the SCADA system shoulders the important tasks of data collection and monitoring of the whole long-distance pipeline, gas transmission management, production scheduling, operation and maintenance coordination in production, and plays a very important role in the whole oil and gas pipeline. In this paper, firstly, the SCADA system for localized long-distance pipelines is explained in detail, including its basic structure and special solutions to problems. Secondly, the AdaBoost algorithm, which combines the MapReduce parallel computing framework, is introduced to collect and process data from the operation logs of the SCADA system and normalize the logs. Finally, to test the interaction between the improved AdaBoost algorithm and the SCADA system, a system test was conducted. The results show that the average latency of scheduling the logs of the SCADA system by AdaBoost algorithm with MapReduce parallel computing framework is only 39.82ms, the average processing speed of the log normalization file data under the multi-threaded mode of the system reaches 86.51GB/s, and the effective accuracy of the fault diagnosis is as high as 90.36%. This shows that the oil and gas pipeline SCADA system interacting with data visualization technology can process operation logs more quickly and can carry out real-time intelligent supervision of the working status and operation parameters of the whole auxiliary system, promoting the intelligent development of the oil and gas pipeline SCADA system.

A non-iterative frame-reduced structured illumination microscopy using checkerboard modulation

Structured illumination microscopy (SIM) is a tremendously potential super-resolution microscopy technique requiring nine raw images to enhance two-fold lateral resolution. For SIM, it is a challenging dilemma to achieve super-resolution imaging with a reduced number of images and fast data processing speed at the same time. Here, we demonstrate a new SIM reconstruction framework that uses only four raw images without requiring extensive iterative computation. The four-frame method is achieved by applying checkerboard pattern illumination modulation to supersede the sinusoidal fringe illumination. It is worth noting that the proposed scheme prominently shortens image acquisition time, combined with a remarkably higher image reconstruction rate compared to current frame-reduced methods. Meanwhile, the reconstruction process is non-iterative and unlimited by the field of view size. Consequently, our work is expected to bring about breakthroughs in facilitating the improvement of real-time live cell observation.

Сокращение времени вычисления операции секционной свертки с помощью учета практической производительности быстрого преобразования Фурье

In digital signal processing the question of the speed of the algorithms speed used is becoming more and more relevant. The convolution and correlation operations used are most often based on standard function libraries, which are focused on reducing data processing time by splitting the source data into sections. With small amounts of data, these algorithms work quite efficiently. However, in practice, with a significant increase in the dimension 
 of the input data, the methods lose quite a lot in the speed of data processing. A method for calculating the convolution of large signals based on the practical performance of the fast Fourier transform is proposed. The optimal size of the section is analyzed, in which the practical performance of existing algorithms remained at a sufficiently high level. Based on the experimental calculations carried out, the optimal dimension of the section used in the convolution calculation formulas was chosen. The proposed method has been tested on published data from various studies. The significant advantages of the proposed method in solving a number of problems are the reduction of the convolution calculation time for long signals by tens of percent and the possibility of fine-tuning the method for specific computing platforms when using preliminary run-time testing on a fast Fourier transform platform of various sizes

Construction of a simulated dynamic model of data packet routing on a telecommunication network fragment

The object of the current research is the process of routing data packets in a telecommunications network. It was established that the state and parameters of data transmission channels and routers could have a negative impact and need to be taken into account in the process of modeling the routing of data packets in telecommunication networks. A model of simulated dynamic modeling of data packet routing in telecommunication networks has been devised and proposed. The suggested model makes it possible to establish quantitative values of the delay time of processing data packets during their routing along a separate segment of the telecommunications network, taking into account the state and parameters of the data transmission channel and routers. It has been established that the achievement of the minimum delay time of data packets during routing is achieved by choosing the path of their transmission under the condition of minimum transmission time by communication lines and the capabilities of routers in terms of their accumulation and service speed. At the same time, the reduction of packet transmission delay time relative to the average for the time network segment can reach from 21 to 38 percent. It is shown that the main factor affecting the value of the delay time is the speed of data processing along the selected path of packet transmission. The number of routing nodes in a separate data transmission path can affect the delay time only if the parameters of the routers are equal compared to others that are included in alternative routes. The model of simulated dynamic modeling of data packet routing reported in this work, unlike the existing ones, takes into account the state and parameters of data transmission channels and routers. It can be used in practical improvement of existing and development of new multi-service telecommunication communication networks

Improving Data Processing Speed on Large Datasets in a Hadoop Multi-node Cluster using Enhanced Apriori Algorithm

For large data, data mining methods were used on a Hadoop-based distributed infrastructure, using map reduction paradigm approaches for rapid data processing. Though data mining approaches are established methodologies, the Apriori algorithm provides a specific strategy for increasing data processing performance in big data analytics by applying map reduction. Apriori property is used to increase the efficiency of level-wise creation of frequent itemsets by minimizing the search area. A frequent itemset’s subsets must also be frequent (Apriori property). If an itemset is rarely, then all of its supersets are infrequent as well. We refined the apriori approach by varying the degree of order in locating frequent item sets in large clusters using map reduction programming. Fixed Pass Combined Counting (FPC) and Dynamic Pass Combined Counting (DPC) is a classical algorithm which are used for data processing from the huge datasets but their accuracy is not up to the mark. In this article, updated Apriori algorithms such as multiplied-fixed-pass combined counting (MFPC) and average time-based dynamic combined counting (ATDFC) are used to successfully achieve data processing speed. The proposed approaches are based on traditional Apriori core notions in data mining and will be used in the map-reduce multi-pass phase by ignoring pruning in some passes. The optimized-MFPC and optimized-ATDFC map-reduce framework model algorithms were also presented. The results of the experiments reveal that MFPC and ATDFC are more efficient in terms of execution time than previously outmoded approaches such as Fixed Pass Combined Counting (FPC) and Dynamic Pass Combined Counting (DPC). In a Hadoop multi-node cluster, this paradigm accelerates data processing on big data sets. Previous techniques were stated in terms of reducing execution time by 60–80% through the use of several passes. Because of the omitted trimming operation in data pre-processing, our proposed new approaches will save up to 84–90% of that time.

BIG DATA TUSHUNCHASI VA HUQUQIY TABIATI

This article describes and analyzes the concept of Big Data, its origin, the opinions of scientists, its legal nature, and its characteristics. Several leading theories and concepts regarding the legal nature and status of Big Data are explored. The content of the theory of information properties (IPT) and the theory of datafication is revealed. The importance of Big Data in determining its legal status is emphasized. Several theories and concepts that are important for understanding and recognizing the material value of Big Data are touched upon. Ownership is considered a fundamental aspect (element) of Big Data ownership, and several theories and concepts are analyzed that offer different approaches to determining the ownership of data. In particular, the content of the theory of the concepts of appropriation, access, and control is revealed. Due to its specific characteristics, such as the volume, variety, and speed of data processing, Big Data creates new problems and issues in the field of legal protection. The activities of international organizations dealing with legal data protection issues are analyzed. The theories and concepts of the transfer of ownership of Big Data and its legal consequences are comparatively studied. The legal status of Big Data in Uzbekistan and its legal framework are highlighted, and the current legislation is analyzed.

Ferroelectric-programmed photonic computing in monolayer WS2

Photonic computing has the potential to significantly improve energy efficiency and data processing speed beyond that of von Neumann architecture. Although various optical processing techniques have been developed during recent two decades, the photonic manipulation is still a big challenging due to the bosonic nature of photons. Herein, we propose a ferroelectric field-controlled photonic computing based on the heterostructure of ferroelectric/van der Waals semiconductor. The strong and tunable electrostatic coupling of ferroelectric (PMN-PT) with monolayer WS2 results in a multi-level (24 bits) photoluminescence (PL) output. Furthermore, combining device modeling with experiments, we find that the multi-level PL output is because of the regulation of ferroelectric polarization on the net recombination rate of WS2. The ferroelectric field-controlled multi-level PL output enables us to design an optical arithmetic operation in the PMN-PT/WS2 heterostructure, which provides an attractive solution for photonic information computing.

Activation Function Dynamic Averaging as a Technique for Nonlinear 2D Data Denoising in Distributed Acoustic Sensors

This work studies the application of low-cost noise reduction algorithms for the data processing of distributed acoustic sensors (DAS). It presents an improvement of the previously described methodology using the activation function of neurons, which enhances the speed of data processing and the quality of event identification, as well as reducing spatial distortions. The possibility of using a cheaper radiation source in DAS setups is demonstrated. Optimal algorithms’ combinations are proposed for different types of the events recorded. The criterion for evaluating the effectiveness of algorithm performance was an increase in the signal-to-noise ratio (SNR). The finest effect achieved with a combination of algorithms provided an increase in SNR of 10.8 dB. The obtained results can significantly expand the application scope of DAS.

Thermal management of the central processing unit cooling system using a cylindrical metal foam heat sink under the influence of magnetohydrodynamic nanofluid flow

PurposeEfficient thermal management of central processing unit (CPU) cooling systems is vital in the context of advancing information technology and the demand for enhanced data processing speeds. This study aims to explore the thermal performance of a CPU cooling setup using a cylindrical porous metal foam heat sink.Design/methodology/approachNanofluid flow through the metal foam is simulated using the Darcy–Brinkman–Forschheimer equation, accounting for magnetic field effects. The temperature distribution is modeled through the local thermal equilibrium equation, considering viscous dissipation. The problem’s governing partial differential equations are solved using the similarity method. The CPU’s hot surface serves as a solid wall, with nanofluid entering the heat sink as an impinging jet. Verification of the numerical results involves comparison with existing research, demonstrating strong agreement across numerical, analytical and experimental findings. Ansys Fluent® software is used to assess temperature, velocity and streamlines, yielding satisfactory results from an engineering standpoint.FindingsInvestigating critical parameters such as Darcy number (10−4 ≤ DaD ≤ 10−2), aspect ratio (0.5 ≤ H/D ≤ 1.5), Reynolds number (5 ≤ ReD,bf ≤ 3500), Eckert number (0 ≤ ECbf ≤ 0.1) , porosity (0.85 ≤ ε ≤ 0.95), Hartmann number (0 ≤ HaD,bf ≤ 300) and the volume fraction of nanofluid (0 ≤ φ ≤ 0.1) reveals their impact on fluid flow and heat sink performance. Notably, Nusselt number will reduce 45%, rise 19.2%, decrease 14.1%, and decrease 0.15% for Reynolds numbers of 600, with rising porosity from 0.85 to 0.95, Darcy numbers from 10−4 to 10−2, Eckert numbers from 0 to 0.1, and Hartman numbers from 0 to 300.Originality/valueDespite notable progress in studying thermal management in CPU cooling systems using porous media and nanofluids, there are still significant gaps in the existing literature. First, few studies have considered the Darcy–Brinkman–Forchheimer equation, which accounts for non-Darcy effects and the flow and geometric interactions between coolant and porous medium. The influence of viscous dissipation on heat transfer in this specific geometry has also been largely overlooked. Additionally, while nanofluids and impinging jets have demonstrated potential in enhancing thermal performance, their utilization within porous media remains underexplored. Furthermore, the unique thermal and structural characteristics of porous media, along with the incorporation of a magnetic field, have not been fully investigated in this particular configuration. Consequently, this study aims to address these literature gaps and introduce novel advancements in analytical modeling, non-Darcy flow, viscous dissipation, nanofluid utilization, impinging jets, porous media characteristics and the impact of a magnetic field. These contributions hold promising prospects for improving CPU cooling system thermal management and have broader implications across various applications in the field.

ДОСЛІДЖЕННЯ ЕФЕКТИВНОСТІ ВИКОРИСТАННЯ РОЗПОДІЛЕНОЇ МАТРИЧНОЇ ФАКТОРИЗАЦІЇ В ПРОМИСЛОВИХ СИСТЕМАХ

The processing of big data is an exceedingly urgent challenge in the functioning of modern information systems. The latest information technologies must be employed to collect, store, and analyze vast amounts of information. Intelligent data processing systems were implemented in numerous fields, particularly in the industry. Smart industrial systems also utilize data from various devices, enabling automated management processes and network component analysis. A prime example of an intelligent industrial system is the smart grid, which efficiently distributes electricity to users by considering demand, network parameters, load, etc. Processing large amounts of information necessitates the use of machine learning methods and mathematical data analysis. Matrix factorization serves as an exemplary technique for transforming information into a more convenient form for further processing, establishing relationships between elements, and optimizing outcomes. In particular, the SVD (Singular Value Decomposition) and Funk-SVD algorithms are employed to address big data processing challenges, and they were discussed in this work. The key features of processing large data volumes in industrial smart grid systems were analyzed in the paper. The advantages of distributed computing for more efficient information analysis were identified. The recommendation algorithms that enable faster and more accurate processing of extensive data were explored in the study. Specifically, the SVD and Funk-SVD algorithms, used in recommendation systems for large data processing, were examined. A method of distributed matrix factorization to provide recommendations to smart grid system users was proposed in the paper. This approach involves the exchange of public data between devices and the local processing of private data. The advantages of this distributed model include flexibility in adjusting parameters, improved calculation accuracy through result exchange between nodes, high data processing speed, and scalability were identified. The conclusion that the proposed method can be effectively used in recommendation systems within the smart grid context, enhancing automated management processes and resource distribution was exclaimed.

ANALYSIS OF DISTRIBUTION OF NO2 POLLUTANTS IN PT. X SANGGAU REGENCY, WEST KALIMANTAN

Air pollution can come from natural activities and human activities. One type of pollutant that needs attention is air pollution caused by exhaust fumes from engine combustion and air pollution due to machines such as steam power plants. PT. X is a company engaged in the industrial sector that processes bauxite into alumina. PT. X is an example of an industry that uses coal and diesel-fired steam power plants for its factory operations. As a result of the fuel combustion process produces several exhaust gases, one of which is nitrogen dioxide, into the surrounding air. If the flue gas from the chimney exceeds the quality standard, it can pose a risk to workers and the surrounding community. Therefore, research was conducted on analyzing the distribution of NO2 pollutants from chimneys at PT. X. The data used are primary and secondary. The primary data is in the form of NO2 concentration in ambient air, while the secondary data is in wind direction and speed in one year. The known secondary data is then processed using the wrplot application so that the results are obtained in the form of the distribution of NO2 pollutants in the air. Based on the results of wind speed and direction data processing in Figure 1, it can be seen that the dominant wind direction blows from east to west with 699 occurrences, with wind speeds mostly occurring between 3.00 – 4.00 MS. Based on the wind rose above, there is no wind with a speed of less than 0.5 m/s or a calm wind. The minimum speed occurs in the range 1.00 – 2.00 m/s and the maximum speed occurs in the range ≥ 7.00 m/s.

INTELLIGENT SYSTEMS FOR FORMING PROJECT TEAMS IN SAFETY-ORIENTED SYSTEMS

Human security project teams are formed in higher education institutions that train qualified civil protection specialists. One of the tasks is to increase the efficiency of forming SOS project teams by HR services, as well as to improve the recruitment and selection procedure using modern information technologies. Developing human resources, improving the quality of higher education for its applicants. Information systems provide high speed data processing, information search, recruitment optimization and candidate analysis. Automation of HR processes helps to reduce the labor intensity and resource costs of tasks. New models, methods, and technologies for processing materials and information about applicants for the purpose of evaluating them for further involvement in the SOS project will contribute to the sustainable development of the organization. The subject of the study is models for automating the selection of personnel in safety-oriented systems with their subsequent formation into project teams of the civil protection service and law enforcement agencies. One of the components of human resource management is the implementation of a subsystem for the assessment and selection of human resources, the initial elements of which are the basis for making personnel decisions on the formation of project teams. The purpose of the study is to formalize the criteria for selecting candidates to reduce the subjectivity of the assessment; optimize and automate the selection process, design expert decision support systems for HR. The article sets the following tasks: to design an information system for the formation of project teams in safety-oriented systems, taking into account the parameters of personal human qualities and professional skills of candidates using information expert systems. To improve the quantitative assessment and qualitative indicators of applicants, it is advisable to formalize the criteria and their weighting coefficients using the theory of qualimetrics and personnel assessment methods. The following research methods were used: system analysis, empirical methods, and project management methodology. The following results have been obtained: a model-scheme of an iterative approach to the development of an information system for human resource management for higher education institutions, taking into account specific learning conditions, has been developed. Conclusions. The methods of evaluation and selection of human resources, as well as the criteria for their selection in complex socio-technical systems are analyzed. The possibilities of automating HR processes and integrating an information system to support the formation of project teams in a safety-oriented system are considered. description of the life cycle of complex systems of a safety-oriented system, namely, the life cycle of such complex socio-technical systems is described, taking into account their characteristics and environment.

Factors affecting real‐time evaluation of muscle function in smart rehab systems

AbstractAdvancements in remote medical technologies and smart devices have led to expectations of contactless rehabilitation. Conventionally, rehabilitation requires clinicians to perform routine muscle function assessments with patients. However, assessment results are difficult to cross‐reference owing to the lack of a gold standard. Thus, the application of remote smart rehabilitation systems is significantly hindered. This study analyzes the factors affecting the real‐time evaluation of muscle function based on biometric sensor data so that we can provide a basis for a remote system. We acquired real clinical stroke patient data to identify the meaningful features associated with normal and abnormal musculature. We provide a system based on these emerging features that assesses muscle functionality in real time via streamed biometric signal data. A system view based on the amount of data, data processing speed, and feature proportions is provided to support the production of a rudimentary remote smart rehabilitation system.