Classification Technology Research Articles

Oil painting image style recognition based on ResNet-NTS network

With the improvement of economic level, cultural and artistic pursuits have become the new life style of people. For painting exhibition style appreciation, the study uses deep learning and neural networks to classify and recognize the style identification of oil painting images. Firstly, the classification technology of residual networks is used to collect features and enhance regions in images of Western oil painting art. Secondly, the residual network is optimized and improved. Finally, attention mechanism and improved activation function are introduced to achieve the recognition effect of oil painting image style. Through comparative experiments, the results show that the improved residual network has an accuracy of 69.38% in style recognition of oil painting datasets. After optimizing with cosine annealing decay strategy, the network testing system model has the highest recognition accuracy of 74.41% for oil painting style data. Finally, the residual network and the network test system are respectively used in the style recognition of Xizang Thangka art dataset, and the accuracy of style recognition of the improved residual network and the network test system is 87.39% and 95.28%, respectively. Therefore, it proves that the residual network and network test system model based on the residual network and network test system model have superiority in the effect of oil painting style recognition, and improve technical support for art dissemination and management.

Statistical analysis of aging micro-characteristics for asphalt binder AFM images based on neural network classification

To further evaluate the effect of aging behavior on microstructure for asphalt binder, the atomic force microscope (AFM) images of asphalt binder were studied by neural network classification technology, and its aging micro-characteristics were analyzed statistically. Firstly, AFM equipment was used to test 90# virgin asphalt binder and styrene–butadiene–styrene (SBS) modified asphalt binder commonly used in engineering, and the typical micromorphology AFM images of asphalt binders were obtained. Subsequently, the asphalt binder AFM images were preliminatively analyzed, and the micro-characteristics of AFM images before and after aging were compared, including the “bee structure” characteristics, distribution law and surface structure roughness. Finally, the asphalt binder AFM images were further analyzed by neural network classification, and the change of “bee structure” was statistically calculated and analyzed, and its aging micro-characteristics were quantitatively evaluated. The results show that it is feasible for neural network classification to be applied to the statistical analysis of asphalt binder AFM images, and it can further describe and evaluate the aging micro-characteristics of asphalt binder. Aging behavior reduces the proportion of intermediate category areas in asphalt binder AFM images and increases the “bee structure” areas. The cumulative percentage curve of asphalt binder AFM images is smoother (each category is more uniform), indicating that the asphalt binder performance tended to be stable after aging. The results further enrich the description of asphalt binder AFM images, and provide a new way to explore the micro-morphology of asphalt binder.

Measures and results of prevention and control on casing deformation and frac-hit in deep shale gas wells in southern Sichuan Basin

Casing deformation and frac-hit pose significant challenges to the development of deep shale gas in southern Sichuan Basin. By analyzing the mechanism and main control factors of casing deformation and frac-hit, two kinds of risk assessment methods were defined, and the overall prevention and control concept and practice were formulated. The results show that initial stress, pore pressure, fault development and large scale fracturing in local block are the main factors leading to the deformation. The development of fracture through well group and uncontrolled fracturing fluid volume are the main factors leading to pressure channeling. Based on this, the risk classification technology of casing deformation and frac-hit is established, and the dual-optimal, dual-control concept and technology are formed. In terms of the prevention and control of casing deformation, the formation of small-diameter bridge plug fracturing, large section combined fracturing, glass beads cementing, single-well staggered and platform straddle fracturing mode, dual-dimension controlled and lift fracturing, hyperbolic diagnosis, etc. Frac-hit prevention and control formed pump sequence optimization mode, physical and chemical temporary plugging and other methods. The above technology achieved casing deformation rate decreased from 50.4% to 25.4%, frac-hit rate decreased from 58.6% to 33.9%, and the average well kilometer EUR reached 0.52–0.7 million square meters, an increase of 7.7% compared with the previous research, with remarkable results.

Influence of Information and Communication Technology Application in Construction Jobsites: A Systematic Review and Bibliometric Analysis

In recent years, the construction industry has witnessed a surge in the adoption and application of emerging technologies. Substantial evidence indicates the impact of these technologies on the lifecycle of construction projects. Among the notable categories of technologies embraced in construction, Information and Communication Technologies (ICTs) stand out. This category encompasses BIM models, reality capture, cloud computing, robotics, and more. However, a literature investigation that specifically focuses on the significant influence of these technologies on construction sites is lacking. To address this gap, this study conducted a systematic literature review, supported by a bibliometric analysis of published articles in the field of construction management. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method, data was sourced from Scopus and Web of Science, covering the period from 2009 to 2023. The findings shed light on nine prominent ICT tools widely adopted on construction sites for project execution, with contributions from 113 countries emphasizing their profound impacts. Despite these positive aspects, this study also identifies notable challenges and provides recommendations for mitigating them. A smart site data integration framework was developed to facilitate the seamless integration of these technologies while ensuring data security. This study provides fundamental insights for future research in this field aimed at informing the construction industry about the importance of embracing cutting-edge technologies for enhanced efficiency on construction jobsites and for timely project delivery.

Decoding cognitive health using machine learning: A comprehensive evaluation for diagnosis of significant memory concern

AbstractThe timely identification of significant memory concern (SMC) is crucial for proactive cognitive health management, especially in an aging population. Detecting SMC early enables timely intervention and personalized care, potentially slowing cognitive disorder progression. This study presents a state‐of‐the‐art review followed by a comprehensive evaluation of machine learning models within the randomized neural networks (RNNs) and hyperplane‐based classifiers (HbCs) family to investigate SMC diagnosis thoroughly. Utilizing the Alzheimer's Disease Neuroimaging Initiative 2 (ADNI2) dataset, 111 individuals with SMC and 111 healthy older adults are analyzed based on T1W magnetic resonance imaging (MRI) scans, extracting rich features. This analysis is based on baseline structural MRI (sMRI) scans, extracting rich features from gray matter (GM), white matter (WM), Jacobian determinant (JD), and cortical thickness (CT) measurements. In RNNs, deep random vector functional link (dRVFL) and ensemble dRVFL (edRVFL) emerge as the best classifiers in terms of performance metrics in the identification of SMC. In HbCs, Kernelized pinball general twin support vector machine (Pin‐GTSVM‐K) excels in CT and WM features, whereas Linear Pin‐GTSVM (Pin‐GTSVM‐L) and Linear intuitionistic fuzzy TSVM (IFTSVM‐L) performs well in the JD and GM features sets, respectively. This comprehensive evaluation emphasizes the critical role of feature selection, feature based‐interpretability and model choice in attaining an effective classifier for SMC diagnosis. The inclusion of statistical analyses further reinforces the credibility of the results, affirming the rigor of this analysis. The performance measures exhibit the suitability of this framework in aiding researchers with the automated and accurate assessment of SMC. The source codes of the algorithms and datasets used in this study are available at https://github.com/mtanveer1/SMC.This article is categorized under: Technologies > Classification Technologies > Machine Learning Application Areas > Health Care

DECODING COVID-19: HARNESSING CNN MODELS FOR CHEST X-RAY CLASSIFICATION

COVID-19 is a new virus that infects the respiratory tract of the upper respiratory system and organs. Based on the worldwide epidemic, the number of illnesses and deaths was growing every day. Chest X-ray (CXR) pictures are beneficial for monitoring lung diseases, especially COVID-19. Deep learning (DL) is a popular computing concept that has been widely used in medical applications. Efforts to automatically diagnose COVID-19 have been beneficial. This study used convolution neural networks (CNN) models to develop a DL technology for binary classification of COVID-19 using CXR pictures. By reducing the number of layers and tweaking parameters, training time was reduced. The suggested model for training loss of 0.0444 and accuracy of 98.53%. In validation it demonstrates even higher proficiency attaining a loss of 0.0181 and accuracy of 99.17%. These findings highlight the need of using deep learning (DL) for early COVID-19 diagnosis and screening. KEYWORDS— CNN, COVID-19, X-ray, Model, Deep convolutional neural networks.

Analysis of Form Two Mathematics Textbook Content for Functional Graph Topic using the Praxeology Method

The use of the praxeology method is very important in knowing the delivery of the content contained in the textbook. However, there is still a lack of research on content analysis in Form Two Functional Graph Topic using the praxeology method. This study aims to analyze the Form Two Mathematics Textbook content for the topic of Functional Graph based on the praxeology method. Data collection was done by content analysis by categorizing the set of praxis (practical) blocks consisting of assignment types (T) and techniques (τ) as well as logos (knowledge) blocks consisting of technology (θ) and theory (Θ). The findings of the study show that there are 18 types of assignments (T), 13 techniques (τ), 10 technologies (θ), and eight theories (Θ) contained in the topic. This study found that six types of assignments (T) did not complete the categories in the prexeology method, one type of assignment (T) did not have technique (τ), one type of assignment (T) did not have theory (Θ) and four types of assignment (T) did not have all three categories of prexeology, namely technique (τ), technology (θ) and theory (Θ). Therefore, based on this study, if the assignment does not complete the praxeology category, it affects the knowledge gained by students in completing the assignment on the topic of Functional Graphs, in addition to facing the limitations of comprehensive knowledge. This research can guide interested institutions in formulating improvements to the content in the mathematics textbook for the topic of Form Two Functional Graph to improve students' understanding of the topic of Functional Graph. Keywords: praxis block set (practical), logos block set (knowledge), Functional Graph topic, praxeology method.

Multi-Task Scenario Encrypted Traffic Classification and Parameter Analysis.

The widespread use of encrypted traffic poses challenges to network management and network security. Traditional machine learning-based methods for encrypted traffic classification no longer meet the demands of management and security. The application of deep learning technology in encrypted traffic classification significantly improves the accuracy of models. This study focuses primarily on encrypted traffic classification in the fields of network analysis and network security. To address the shortcomings of existing deep learning-based encrypted traffic classification methods in terms of computational memory consumption and interpretability, we introduce a Parameter-Efficient Fine-Tuning method for efficiently tuning the parameters of an encrypted traffic classification model. Experimentation is conducted on various classification scenarios, including Tor traffic service classification and malicious traffic classification, using multiple public datasets. Fair comparisons are made with state-of-the-art deep learning model architectures. The results indicate that the proposed method significantly reduces the scale of fine-tuning parameters and computational resource usage while achieving performance comparable to that of the existing best models. Furthermore, we interpret the learning mechanism of encrypted traffic representation in the pre-training model by analyzing the parameters and structure of the model. This comparison validates the hypothesis that the model exhibits hierarchical structure, clear organization, and distinct features.

The use of intelligent real-time image acquisition system using data mining technology in news acquisition and editing practice

Aiming to address the timely dissemination of news information, this work explores the clever utilization of data mining (DM) technology and deep learning (DL) algorithms to construct an intelligent real-time news image acquisition system to meet the urgency of news dissemination needs. First, this work introduces an intelligent real-time news image acquisition system and provides a detailed analysis of its principles and advantages. Throughout this process, the crucial role of DM technology in news image classification and automation is emphasized, especially in dealing with rapidly evolving news events. Next, the work establishes an intelligent real-time news image acquisition model based on DL algorithms, which integrates the essence of DM technology. Through this fusion, the research objective is to enhance the performance of the news image acquisition system to achieve higher real-time and accuracy, which is vital for the swift delivery of news information. Finally, this work investigates the application of the intelligent news image acquisition system in network communication to ensure its adaptability to various network communication scenarios while maintaining accuracy and real-time capabilities. The research results demonstrate that the application of DM technology in combination with DL algorithms can effectively meet the practical needs of the news industry, enhancing the automation of news image processing and enabling faster information delivery to the audience. Notably, the AlexNet model employed performs exceptionally well, achieving recognition rates of up to 99.6% after data augmentation or equalization processing, with an accuracy of 90.9% and a high specificity of 93.38%. This indicates outstanding overall classification accuracy and negative class accuracy, even when distinguishing between news and non-news scenarios. These results clearly underscore the connection between DM technology and news acquisition and editing practices, and emphasize its potential to improve the efficiency and accuracy of real-time information dissemination. The research’s contribution and innovation lie in the fusion of DM technology with DL algorithms to build an intelligent real-time news image acquisition system. This fusion enhances the automation and classification performance of news images, thereby improving the real-time and accuracy of news information. Furthermore, the work strongly emphasizes improving the real-time and accuracy of the news image acquisition system to ensure the swift delivery of information, which is of utmost importance in rapidly changing news events.

Neural Technologies for Objects Classification with Mobile Applications

This paper is related to the study of the features of the neural technologies’ application, in particular, ResNet neural networks for the classification of objects in photographs. The work aims to increase the accuracy of recognition and classification of objects in photographs by using various models of the ResNet neural network. The paper analyzes the features of the application of the corresponding models in comparison with other architectures of deep neural networks and evaluates their efficiency and accuracy in the classification of objects in photographs. The process of data formation for training neural networks, their processing and sorting is described. A web application and a mobile application for recognizing and classifying objects in a photo were also developed. A system for classifying objects, in particular airplanes in photographs, was developed using neural network technologies. It gives a recognition and classification accuracy of about 95%. Research results of ResNet models are of great practical importance, as they can improve the classification accuracy of various images. Features of ResNet, such as the use of skip connections or residual connections, make it effective in the relevant tasks. The results of the study will help to implement ResNet in various fields, including medicine, automatic pattern recognition and other areas where the classification of objects in photographs is an important task.

Advancing body composition assessment in patients with cancer: First comparisons of traditional versus multicompartment models

Background and aimsMeasurement of body composition using computed tomography (CT) scans may be a viable clinical tool for low muscle mass assessment in oncology. However, longitudinal assessments are often infeasible with CT. Clinically accessible body composition technologies can be used to track changes in fat-free mass (FFM) or muscle, though their accuracy may be impacted by cancer-related physiological changes. The purpose of this study was to examine the agreement among accessible body composition method with criterion methods for measures of whole-body FFM measurements and, when possible, muscle mass for the classification of low muscle in patients with cancer. MethodsPatients with colorectal cancer were recruited to complete measures of whole-body DXA, air displacement plethysmography (ADP), and bioelectrical impedance analysis (BIA). These measures were used alone, or in combination to construct the criterion multicompartment (4C) mode for estimating FFM. Patients also underwent abdominal CT scans as part of routine clinical assessment. Agreement of each method with 4C model was analyzed using mean constant error (CE = criterion – alternative), linear regression including root mean square error (RMSE), Bland-Altman limits of agreement (LoA) and mean percentage difference (MPD). Additionally, appendicular lean soft tissue index (ALSTI) measured by DXA and predicted by CT were compared for the absolute agreement, while the ALSTI values and skeletal muscle index by CT were assessed for agreement on the classification of low muscle mass. ResultsForty-five patients received all measures for the 4C model and 25 had measures within proximity of clinical CT measures. Compared to 4C, DXA outperformed ADP and BIA by showing the strongest overall agreement (CE = 1.96 kg, RMSE = 2.45 kg, MPD = 98.15 ± 2.38%), supporting its use for body composition assessment in patients with cancer. However, CT cutoffs for skeletal muscle index or CT-estimated ALSTI were lower than DXA ALSTI (average 1.0 ± 1.2 kg/m2) with 24.0% to 32.0% of patients having a different low muscle classification by CT when compared to DXA. ConclusionsDespite discrepancies between clinical body composition assessment and the criterion multicompartment model, DXA demonstrates the strongest agreement with 4C. Disagreement between DXA and CT for low muscle mass classification prompts further evaluation of the measures and cutoffs used with each technique. Multicompartment models may enhance our understanding of body composition variations at the individual patient level and improve the applicability of clinically accessible technologies for classification and monitoring change over time.

Underwater acoustic analysis reveals unique pressure signals associated with aircraft crashes in the sea: revisiting MH370

Data analysis from the hydroacoustic stations of the Comprehensive Nuclear-Test-Ban Treaty Organization has unveiled distinctive pressure signals linked to aircraft crashes of varying sizes in the ocean. Notably, these signals were detected at distances ranging from two to five thousand kilometres, highlighting the efficacy of underwater acoustic technology in event identification and classification in marine environments. In this study, we investigate the plausibility of an aircraft, such as Malaysian Airlines Flight 370 (MH370), crashing into the sea leaving a discernible pressure signal at distant hydrophones. Consequently, we focus on recordings obtained from the hydroacoustic monitoring stations located at Cape Leeuwin and Diego Garcia, within a few minutes of the last satellite ping on the 7th arc, associated with the assumed crash time and location. Among the available data, only one relevant signal has emerged as a potential candidate, albeit recorded at a single station out of the two stations available. To ensure a comprehensive analysis, we also examine the time frame and location of the airplane along its initial route. Though no corresponding signal was observed. Nevertheless, the findings in this study narrow down the range of possibilities and present a novel scientific approach to investigate such incidents. These findings contribute to our understanding of acoustic signals associated with aircraft crashes at sea. They emphasise the potential for hydrophones to detect events even when the signal travels long distances through land. Ultimately, this research offers recommendations for conducting on-site experiments involving controlled explosions with energy levels similar to the impact of MH370 along the 7th arc. The aim is to encourage pertinent authorities to implement actions that could reveal insights into the destiny of MH370 specifically. Additionally, this initiative seeks to establish a comprehensive framework for addressing comparable incidents in the broader ocean context.

Review of energy-efficient HVAC technologies for sustainable buildings

This review paper provides a comprehensive examination of energy-efficient Heating, Ventilation, and Air Conditioning (HVAC) technologies for sustainable buildings. The focus is on exploring the latest advancements, benefits, challenges, and future prospects in the realm of HVAC systems designed to enhance energy efficiency and promote sustainability in building operations. The review begins with an overview of the importance of energy-efficient HVAC technologies in the context of sustainable building design and operation. It underscores the critical role of HVAC systems in reducing energy consumption, minimizing environmental impact, and enhancing occupant comfort and well-being. The paper delves into various categories of energy-efficient HVAC technologies, including advanced heating and cooling systems, ventilation strategies, and smart controls. Each category is examined in detail, highlighting key features, performance metrics, and real-world applications. Furthermore, the review evaluates the benefits associated with energy-efficient HVAC technologies, such as significant energy savings, reduced operating costs, improved indoor air quality, and enhanced building resilience. It also discusses the potential challenges and barriers to adoption, such as high upfront costs, complexity of implementation, and retrofitting existing buildings. The paper explores emerging trends and innovations in the field of energy-efficient HVAC technologies, including the integration of renewable energy sources, smart sensors and actuators, and predictive maintenance algorithms. These advancements have the potential to further optimize energy performance, increase system reliability, and enable proactive management of HVAC systems. In conclusion, the review emphasizes the importance of energy-efficient HVAC technologies as a cornerstone of sustainable building practices. It underscores the need for continued research, innovation, and collaboration among stakeholders to overcome existing challenges and unlock the full potential of energy-efficient HVAC systems in contributing to a more sustainable built environment. Overall, this comprehensive review provides valuable insights into the current state of energy-efficient HVAC technologies, their applications, benefits, and challenges, while also highlighting opportunities for future advancements and their crucial role in achieving sustainability goals in the building sector.

STRESS, EQUIVALENT STRAIN AND DEFORMATION FOR MACHINING OPERATION UTILIZING EXPLICIT DYNAMIC ANALYSIS FOR VARIOUS MATERIALS

Subtractive and additive manufacturing methods constitute the two main categories of modern manufacturing technology used in the manufacturing sector. The subtractive method is used for material removal and is performed in (Brass, Aluminum and Teflon), the machining process is achieved using CNC (Computer Numerical Method) turn machine. The main objective of the paper is to perform FEA (Finite Element Analysis) over the three material (Brass, Aluminum and Teflon). The CNC machine is used to perform a machining over the three-material stated above, but within the CNC machine there is no provision for achieving the various values of (stress, strain and deformation) during the machining operation. During the machining process, it’s very difficult to get and accurate value of stress for the tool and raw (test) material, so Ansys FEA analysis method is adopted to predict the parameter like stress, strain and total deformation. The analysis part is achieved by the developing the CAD model using Solid work and FEA analysis using Ansys and thereby the output will be helpful to understand the various stress parameters. The results highlight that Teflon has a higher value for total deformation followed by aluminum and brass. The equivalent strain for the Teflon is higher and followed by brass and aluminum. The stress is acting in axial and compressive direction, so brass have a higher value followed by aluminum and Teflon. This method and analysis procedure can be adopted for understanding the deformation, stress and stain acting on any material, which will be highly useful for material of higher with a higher hardness value.

Advancing Fruit Image Classification with State-of-the-Art Deep Learning Techniques

Fruit image classification technology using deep learning is making significant contributions in the agriculture and food retail sectors, promising to increase efficiency and productivity. However, there is an identified knowledge gap in dealing with the considerable variation in fruit appearance caused by factors such as type, size, color, and lighting conditions, as well as the precise identification of damage or disease. This research focuses on applying the developed Convolutional Neural Network architecture to fill this gap by using it in an extensive and diverse dataset, covering 67,692 image files categorized into 131 fruit classes. The training process showed substantial accuracy improvement, with training accuracy reaching 98.39% and validation accuracy at 90%, while training loss decreased to 0.0430 and validation loss to 0.2991. In the advanced stage of training, the training accuracy peaked at 99.43% in the 59th epoch with a shallow loss of 0.0251. However, the validation loss showed variation, indicating room for improvement in model generalization. The findings provide insight into the potential and challenges of applying Convolutional Neural Network models and fruit image classification with improved fruit sorting accuracy. Contribution to the literature in the field of information technology and agriculture by showing deep learning models can be improved to address the issue of fruit image variability.

Application of LA-UNet network model in remote sensing classification of urban green space

The accurate identification and monitoring of urban green space is of great significance in urban planning and ecological management. In view of the complex background of urban green space, the traditional remote sensing classification technology is prone to the problem of misalignment and adhesion. Taking Yuhua District of Changsha City as the research area and Gaofen-2 (GF-2) remote sensing image as the data source, we proposed a remote sensing classification method for urban green space based on the LA-UNet model, which was based on the UNet model. We introduced the DWTCA channel attention mechanism module to improve the attention of the network to green space information, and used the CARAFE module to up sample the extracted features to achieve accurate classification of trees, shrubs and other land types in the complex background of the city. The results showed that the LA-UNet model had the best classification effect of urban green space when using standard false color remote sensing images. The overall accuracy and mean intersection over union were 96.3% and 90.9%, which were 2.8% and 6.1% higher than the UNet model, respectively. In the Potsdam public dataset, the overall accuracy and mean intersection over union of the LA-UNet model were also better than those of the UNet model, which increased by 0.9% and 1.8%, respectively, indicating that the LA-UNet model had good robustness and versatility. In summary, the proposed LA-UNet model could effectively alleviate the problems of misalignment and adhesion of urban green space, with advantages in the remote sensing classification of urban green space. The improved LA-UNet model had a smaller parameter volume than the UNet model, which could effectively improve the classification accuracy of urban green space. This study would provide a methodological reference for the accurate classification and understanding the spatial distribution of urban green space.

Spectrometer-Less Remote Sensing Image Classification Based on Gate-Tunable van der Waals Heterostructures.

Remote sensing technology, which conventionally employs spectrometers to capture hyperspectral images, allowing for the classification and unmixing based on the reflectance spectrum, has been extensively applied in diverse fields, including environmental monitoring, land resource management, and agriculture. However, miniaturization of remote sensing systems remains a challenge due to the complicated and dispersive optical components of spectrometers. Here, m-phase GaTe0.5Se0.5 with wide-spectral photoresponses (250-1064nm) and stack it with WSe2 are utilizes to construct a two-dimensional van der Waals heterojunction (2D-vdWH), enabling the design of a gate-tunable wide-spectral photodetector. By utilizing the multi-photoresponses under varying gate voltages, high accuracy recognition can be achieved aided by deep learning algorithms without the original hyperspectral reflectance data. The proof-of-concept device, featuring dozens of tunable gate voltages, achieves an average classification accuracy of 87.00% on 6 prevalent hyperspectral datasets, which is competitive with the accuracy of 250-1000nm hyperspectral data (88.72%) and far superior to the accuracy of non-tunable photoresponse (71.17%). Artificially designed gate-tunable wide-spectral 2D-vdWHs GaTe0.5Se0.5/WSe2-based photodetector present a promising pathway for the development of miniaturized and cost-effective remote sensing classification technology.

Research on target characteristics and classification technology of small UAV

Research on target characteristics and classification technology of small UAV

Available rehabilitation technology with the potential to be incorporated into the clinical practice of physiotherapists: A systematic review.

The development of prototypes capable of intervening in the area of rehabilitation in physical therapy clinical practice activities that were previously carried out in a traditional way, that is, manually, demonstrates how technology is having an impact on professional careers such as physiotherapy. The purpose of this study is to present a comprehensive examination of various technologies employed in the facilitation of patient rehabilitation, with a focus on their potential integration within the clinical practice of physical therapists. We conducted a systematic search in four electronic databases (CINAHL, Embase, PEDro, and PubMed) for research on rehabilitation technologies. The eligible studies should demonstrate a clear utilization of technology in various aspects of the clinical approach to the rehabilitation process and have been published between 2000 and 2021 in either Portuguese or English. A total of 18 articles that satisfied the selection criteria were included in the study. The studies were classified into four distinct categories of rehabilitation technologies, which were determined by the specific characteristics of the technology employed and its integration with the therapeutic approach to rehabilitation. These categories include digital technologies, artificial intelligence and/or robotics, virtual technologies, and hybrid technologies. Rehabilitation technologies possess the capacity to effectively facilitate clinical activities performed by physical therapy professionals, including injury prevention, movement monitoring, and coordination of rehabilitation programs, with minimal or negligible intervention from the physical therapist. Further research is required to ascertain the precise capabilities of various technologies in collaborating with physiotherapists to deliver comprehensive care for patients' physical well-being, encompassing both therapeutic and preventive approaches. PROSPERO registration number CRD42020222288.

Natural Language Processing Patents Landscape Analysis

Understanding NLP patents provides valuable insights into innovation trends and competitive dynamics in artificial intelligence. This study uses the Lens patent database to investigate the landscape of NLP patents. The overall patent output in the NLP field on a global scale has exhibited a rapid growth over the past decade, indicating rising research and commercial interests in applying NLP techniques. By analyzing patent assignees, technology categories, and geographic distribution, we identify leading innovators as well as research hotspots in applying NLP. The patent landscape reflects intensifying competition between technology giants and research institutions. This research aims to synthesize key patterns and developments in NLP innovation revealed through patent data analysis, highlighting implications for firms and policymakers. A detailed understanding of NLP patenting activity can inform intellectual property strategy and technology investment decisions in this burgeoning AI domain.