Digital Recognition Research Articles

The socio-aesthetic construction of meaning in digitally mediated environments: a digital sensemaking approach

AbstractSensemaking has recently been identified as a driver of society developments, in particular in the context of designing a reasonable, valuable, and fair life. Since the construction of meaning is a crucial momentum in sensemaking processes, the authors investigate how meaning can be constructed in a sustaining form by utilizing digital means of expression, articulation, sharing of information, and creation of artscience artefacts. The authors report on results of exploring cyber-physical-systems with performative methodologies in the context of sensemaking to identify sensemaking processes of entering digital environments and share meaning-making activities through interaction. The collected data from two artscience studies reveal that activities beyond cognition facilitate sensemaking. Aesthetics and embodiment in performing actions are understood to play a role in sensemaking and subsequently effect on the construction of meaning. To investigate the role of the body and aesthetics in sensemaking in digital environments, we were particularly interested in sensemaking through embodied agency and aesthetic awareness, drawing from kinesthetic awareness of performance artists. In the performative activities digital behavior recognition and human task behavior were coupled, on the one hand by performers exploring digital environments actively reflecting on their performative process, on the other hand by a performance artist and choreographer creating performative experiences for audiences. It has been demonstrated in cyber-physical settings and can be utilized in upcoming developments further integrating virtual and physical worlds.

Digital Dance Movement Recognition and Correction System Combining Human Skeletal Information

Abstract With the development of digital technology, digital dance movement recognition and correction has become a hot research topic. This study focuses on a movement recognition system that incorporates human skeletal information and aims to improve dance movements’ accuracy and correction efficiency. This study develops a digital dance movement recognition and correction system that combines human lean information. This system can recognize and correct dance movements accurately by improving the spatio-temporal graph convolutional network (ST-GCN). The study employs a spatio-temporal graph representation of the human skeleton and spatial graph convolution technique, and enhances the system’s movement recognition capability through an adaptive graph convolution module. The experimental results show that the system achieves an average accuracy of 99.3% in dance movement recognition, 82% and 92% on the publicly available datasets UTKinect and MSRAction3D, respectively, and 95% on the dance movement dataset ETHDance constructed in this study. In addition, by introducing channel, spatial and temporal attention mechanisms, the system also shows high efficiency in dance movement correction. For the correction test of 10 basic dance movements, the correction accuracy is more than 95%, significantly higher than the 69.91% of the traditional method. This study improves the accuracy of dance movement recognition and provides adequate technical support for dance teaching and practicing.

Digital Forensic Based Object Recognition for Enhanced Crime Scene Interpretation

This research introduces a novel and comprehensive framework for digital forensics-based crime scene interpretation. The proposed framework comprises five algorithms, each serving a distinct purpose in enhancing image quality, extracting features, matching, and constructing a database, recognizing, and reconstructing objects in 3D, and conducting context-aware analysis. An ablation study validates the necessity of each algorithmic step. The framework consistently outperforms existing methods in terms of accuracy, precision, recall, and processing time. A detailed comparative analysis of parameters further highlights its cost-effectiveness, moderate complexity, superior data integration, and scalability. Visualizations underscore its dominance across multiple metrics and parameters, positioning it as an advanced solution for digital forensic-based object recognition in crime scene interpretation.

Investigation on Analog and Digital Modulations Recognition Using Machine Learning Algorithms

Investigation on Analog and Digital Modulations Recognition Using Machine Learning Algorithms

Data Testing in Digital Transmission: Tamil Literature

The developing area of Optical Character Recognition (OCR) is digital handwriting recognition. Manual writing is replaced by a digital writing pad. The font and shape of the letters vary while writing digitally. The writer’s digital pen pressure and position on the digital pad cause covert text file problems during OCR recognition. When converting OCR to text, an error occurs because of the variations in letter shapes. In languages like Tamil, Chinese, Arabic, and Telugu, where the alphabet is made up of bends, curves, and rings, the aforementioned issue occurs. Tamil has more word mistakes in OCR-to-text conversion because the alphabet comprises curves and angles that must be correctly transcribed. The ResNet (Residual Neural Network) Two-Stage Bottleneck Architecture (RTSBA) is suggested in this paper. In order to recognize text written in Tamil on a digital writing pad, this article suggests using ResNet (Residual Neural Network) Two-Stage Bottleneck Architecture (RTSBA). The suggested RTSBA reduces the complexity of the Tamil alphabet recognition problem by using two distinct phases of neural networks. There are fewer inputs and variables in the early stages. Time and computational complexity are minimized in the last phase. A two-channel and two-stream transformer, long short-term memory, Inception-v3, recurrent neural networks, convolutional neural networks, and other conventional algorithms have been compared to the suggested algorithm. The digital writing pad-handwritten and HP lab datasets demonstrate the effectiveness of proposed methods like RTSBA, which yield accuracy rates of 98.7% and 97.1%, respectively.

СОВЕРШЕНСТВОВАНИЕ АЛГОРИТМА МАШИННОГО ЗРЕНИЯ В БИОТЕХНИЧЕСКИХ СИСТЕМАХ С ПРИМЕНЕНИЕМ НЕЙРОННЫХ СЕТЕЙ

A review of the hardware design of machine vision systems is given in the work; the basic principles of image processing of biotechnical systems and the corresponding mathematical apparatus are considered using the example of the use of machine vision technology in digital dermatoscopy. The digital information extracted by the computer vision system is transferred to special software for image processing using machine learning methods, among which the work highlights the following: neural networks, regression, classification, and object detection. A classification of neural networks that are used for computer vision is given and a brief description of their practical application is given. The considered methods of computer vision systems in biotechnological practice using convolutional neural networks open up opportunities for improving the quality of visual diagnostics. A comparison with previously known methods for classifying digital objects was carried out in the work to analyze the effectiveness of using CNN. Analysis of the digital object by a convolutional neural network using the Statistica software package revealed different color regions. The accuracy of classification of areas of a digital object was 94.7%, which indicates a high accuracy of digital object recognition using CNN and is 1.5% more accurate than statistical classification methods.

Automated identification of kinetics model in elastomer vulcanization using a rheometer MDR and Rubber-K pattern recognition software

This research developed a novel tool for the automatic characterization of elastomers during vulcanization. For this task, robust algorithms for digital image processing and pattern recognition related to curing kinetics were generated and integrated into Rubber-K software. Rheometer tests were performed under ASTM D2084 standard. Experimental data are imported in portable document format and fit the models established by Kamal-Ryan and Isayev-Deng, using a system of first-order ordinary differential equations. During the fitting of the experimental data, the reduced gradient method is used to minimize the error in the objective function. The models used in the algorithms allow higher accuracy and numerical stability compared to similar applications. Rubber-K software provides relevant information to the user during the injection molding parameterization process, allowing production optimization and significantly reducing non-conforming parts. In order to validate the results and accuracy of Rubber-K software, it was compared with data published by other software developers and similar models, whose findings confirm the power and applicability of the software.

Проблема цифрового распознавания поведения личности в условиях современных вызовов: социально-философский и теологический анализ

Introduction. The article examines the problem of digital personality recognition as one of the dimensions of artificial intelligence from the perspective of socio-philosophical and theological analysis. Theoretical analysis. One of the distinctive features of the scientific and technological development of modern society is that various artificial intelligence (AI) systems have moved from the category of science fiction, utopian projects, innovative developments, prototypes and market innovations to the category of familiar and little-noticed elements of everyday life. This technology, also known as the Internet of Behavior, involves identifying and assessing an individual’s behavior both from the point of view of compliance with requirements and from the point of view of identifying patterns of individual behavior that can become the basis for his identification. The prerequisites and conditions for the emergence of the phenomenon of “golemization” of the individual are analyzed, i.e. its reduction to a set of external physical actions and manifestations without taking into account internal motives as one of the risks that require social philosophical and theological reflection. Conclusion. Within the framework of socio-philosophical and theological discourse, digital recognition of personal behavior can have a positive meaning, because increases attention to responsibility for one’s actions and potentially leads to a decrease in crime rates, as well as a negative value due to the possibility of creating virtual identities that differ from a person’s true identity.

PPFGED: Federated learning for graphic element detection with privacy preservation in multi-source substation drawings

In digital recognition of substation drawings, a significant challenge is how to accurately detect complex graphic elements in each drawing. Existing detection schemes often operate in isolation, with data dispersed across multiple sources, which impedes the development of high-accuracy models. A straightforward solution of consolidating drawings from different substations for training does not satisfy the stringent security requirements of substations. To address these challenges, we propose a novel graphic element detection framework based on federated learning for multi-source substation drawings. Our framework involves a server provider, multiple power companies, and distributed substations, and it employs a universal model generation scheme that protects data privacy. Local substations utilize the designed universal graphic element extraction scheme to categorize drawings and extract smaller elements, achieving enhanced accuracy. Subsequently, we design a privacy-enhanced diffusion model for substations to protect elements before uploading them. Power companies then train local model and apply a designed dimension-compressed local differential privacy scheme to the model parameters to protect the training process. To deter server provider from maliciously exploiting model, a game theory-based optimization solution is designed between server provider and power companies. Finally, experiments conducted using substation drawings provided by multiple cooperating units demonstrate that our framework can accurately perform drawing classification and graphic element extraction, and while obtaining the strongest privacy guarantees and low time cost, it achieves an intelligent system for graphic element detection with an accuracy of 88.14% across different regional substations.

Integrated In-Memory Sensor and Computing of Artificial Vision Based on Full-vdW Optoelectronic Ferroelectric Field-Effect Transistor.

The development and application of artificial intelligence have led to the exploitation of low-power and compact intelligent information-processing systems integrated with sensing, memory, and neuromorphic computing functions. The 2D van der Waals (vdW) materials with abundant reservoirs for arbitrary stacking based on functions and enabling continued device downscaling offer an attractive alternative for continuously promoting artificial intelligence. In this study, full 2D SnS2 /h-BN/CuInP2 S6 (CIPS)-based ferroelectric field-effect transistors (Fe-FETs) and utilized light-induced ferroelectric polarization reversal to achieve excellent memory properties and multi-functional sensing-memory-computing vision simulations are designed. The device exhibits a high on/off current ratio of over 105 , long retention time (>104 s), stable cyclic endurance (>350 cycles), and 128 multilevel current states (7-bit). In addition, fundamental synaptic plasticity characteristics are emulated including paired-pulse facilitation (PPF), short-term plasticity (STP), long-term plasticity (LTP), long-term potentiation, and long-term depression. A ferroelectric optoelectronic reservoir computing system for the Modified National Institute of Standards and Technology (MNIST) handwritten digital recognition achieved a high accuracy of 93.62%. Furthermore, retina-like light adaptation and Pavlovian conditioning are successfully mimicked. These results provide a strategy for developing a multilevel memory and novel neuromorphic vision systems with integrated sensing-memory-processing.

Dendrogram-based Heterogeneous Learners for Automatic Modulation Classification in DSTBC-OFDM Systems

Software-Defined Radios (SDRs) have a crucial role in dynamic spectrum sensing and sharing as they can quickly adapt to changes in their environment. Digital Modulation Recognition (DMR) enables this process by giving SDR the ability to recognize the received signal modulation format to make intelligent and autonomous decisions to switch on the optimal modulation scheme. However, with the deployment of the Distributed Space-Time Block Coding Orthogonal Frequency Division Multiplexing (DSTBC-OFDM) signals that support MIMO systems, that provides spatio-temporel multiplexing, new and challenging signal identification problems have emerged.This paper proposes a robust DMR method for relaying Space-Time Block Coding (STBC) Orthogonal Frequency Division Multiplexing (OFDM) systems. The proposed classifier is built using heterogeneous base classifiers namely, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RFC), based on a Dendrogram or decision tree structure.The Dendrogram-based Heterogeneous Learners (DHL) classifier were obtained via Ascendant Hierarchical Clustering (AHC) and by employing Higher-Order Moment (HOMs) and Higher-Order Cumulants (HOCs) as features. Moreover, we propose a grid search-based hyperparameter tuning for DHL to produce the best structure and optimize the performance.

Developing a Neural Network-based Model for Identifying Medicinal Plant Leaves using Image Recognition Techniques

Herbal plants play a vital role in human health and the environment, as they can provide both medical benefits and oxygen. Many herbal plants contain valuable therapeutic elements that can be passed down to future generations. Traditional methods of identifying plant species, such as manual measurement and examination of characteristics, are labor-intensive and time-consuming. There has been a push to develop more efficient methods using technology, such as digital image processing and pattern recognition techniques to address this. The proper identification of plant methods using computer vision and neural network techniques has been proposed. This approach involves neural network models such as CNN, ALexnet and ResNet for identifying the medical plants based on their respective features. Classification metrics give the 96.82 average accuracies. These results have been promising, and further research will involve using a larger dataset and going more into deep-learning neural networks to improve the accuracy of medicinal plant identification. It is hoped that a web or mobile-based system for automatic plant identification can help increase knowledge about medicinal plants, improve species identification techniques, and protect endangered species.

Developing A Neural Network-Based Model for Identifying Medicinal Plant Leaves Using Image Recognition Techniques

Herbal plants contribute an important role in people's health and the environment, as they can provide both medical benefits and oxygen. Many herbal plants contain valuable therapeutic elements that can be passed down to future generations. Traditional methods of identifying plant species, such as manual measurement and examination of characteristics, are labor-intensive and time-consuming. To address this, there has been a push to develop more efficient methods using technology, such as digital image processing and pattern recognition techniques. The exact recognition of plants uses methodologies like computer vision and neural networks, which have been proposed earlier. This approach involves neural network models such as CNN, ALexnet, and ResNet for identifying the medical plants based on their respective features. Classification metrics give the 96.82 average accuracies. These results have been promising, and further research will involve using a larger dataset and going more into deep-learning neural networks to improve the accuracy of medicinal plant identification. It is hoped that a web or mobile-based system for automatic plant identification can help increase knowledge about medicinal plants, improve techniques for species recognition, and participate in the preservation of species that are considered ad endangered.

Classification of sugar using digital imaging and pattern recognition techniques

This work presents a new analytical methodology based on the use of digital images and multivariate analysis for the classification of sugar samples based on their color. Two studies were evaluated. The first involved the discrimination of refined (RS) and unrefined sugar (US) samples. The second study involved the classification of sugar samples into three different classes: refined sugar for the external market (EMRS); refined sugar for retail (RRS); and US. The frequency distribution of color indices in the red, green, blue, hue, saturation, intensity, and grayscale channels were obtained from digital images. Classification models based on partial least squares discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) were developed. The best results obtained for the studies with two (97.4 % accuracy) and three (95.7 % accuracy) classes were achieved by applying the genetic algorithm (GA) in association with the linear discriminant analysis (GA-LDA) on the datasets. The proposed method offers several advantages, including low cost, simplicity, absence of chemical reagents, and non-destructiveness of the sample.

An Attention-Based Fusion of ResNet50 and InceptionV3 Model for Water Meter Digit Recognition

Digital water meter digit recognition from images of water meter readings is a challenging research problem. One key reason is that this might be a lack of publicly available datasets to develop such methods. Another reason is the digits suffer from poor quality. In this work, we develop a dataset, called MR-AMR-v1, which comprises 10 different digits (0 to 9) that are commonly found in electrical and electronic water meter readings. Additionally, we generate a synthetic benchmarking dataset to make the proposed model robust. We propose a weighted probability averaging ensemble-based water meter digit recognition method applied to snapshots of the Fourier transformed convolution block attention module (FCBAM) aided combined ResNet50-InceptionV3 architecture. This benchmarking method achieves an accuracy of 88% on test set images (benchmarking data). Our model also achieves a high accuracy of 97.73% on the MNIST dataset. We benchmark the result on this dataset using the proposed method after performing an exhaustive set of experiments.

Applying Deep Learning and Machine Learning Algorithms for The Identification of Medicinal Plant Leaves Based on Their Spectral Characteristics

The study and consideration of medicinal plants have been ongoing throughout history due to their significant role in maintaining the well-being of mammals. Although identifying medicinal plants can be a valuable skill, it is often time-consuming, tedious, and requires the expertise of a specialist. The project works on the technique of image processing, which identifies the various medicinal plants. There has been a strong emphasis on improving efficiency through the application of technology, with a focus on incorporating digital image processing and pattern recognition techniques. To ensure accurate plant identification, proposals involving the application of computer vision neural network techniques have been advanced. This approach involves neural network models such as CNN, SVM, KNN, and Navie Bay for identifying the medical plants based on their respective features. After the validation step, the project provides a classification of 92.3 precision and 90.56 F1 score.

Deep learning-based autonomous real-time digital meter reading recognition method for natural scenes

Natural scenes with variable illumination, variable target scale and angular tilt pose significant challenges to the autonomous recognition of digital meter readings. Based on this, this paper proposes a deep learning-based autonomous real-time digital meter reading recognition method for natural scenes. First, the YOLO-style corner point detection method (YOLO-CPDM) for the reading area is proposed by reconstructing the detection heads and incorporating the corner detection loss function. Its localization accuracy is further refined by embedding attention mechanism module, implementing dynamic loss function and enhancing training data diversity through offline augmentation techniques like image rotation and flipping. Then, the detected corner points are used to geometrically correct the distorted reading area by perspective transformation to mitigate the interference caused by the shooting angle. Next, the YOLO-style end-to-end reading recognition method (YOLO-EERRM) is proposed to accurately extract the characters in the reading area. Finally, the validity of the YOLO-CPDM and YOLO-EERRM was verified on a produced dataset named SYSU-DM and 2 public datasets. Compared with the State of the arts (SOTA) keypoint detection model, the mean Average Precision @ 50:95 scores of the YOLO-CPDM improved by 2.8, 4.1, and 1.1 points, respectively, while the inference latency was only 5.3 ms, and YOLO-EERRM achieved 100 % accuracy and 3.1 ms inference latency on the SYSU-DM dataset. Statistically, the complete digital meter reading recognition method has 99.6 % accuracy and 8.6 ms inference latency, indicating that the system has high recognition accuracy and practicality.

Эмоции в архитектуре

The article deals with the phenomenon of emotions in architecture: emotions as an integral part of architecture, a driving force of architecture, and a component of the creative design process. The article attempts to consider the aspects of this issue, and, based on the collected data, develop a generalizing model – an architectural project of a Museum of Emotions or an object, which functional programme includes classification, demonstration of emotions to the viewer, identification of relationships between different emotions and methods of their display by architectural facilities. Also the article deals with the concepts of "sensory architecture - the impact of architecture on the emotional picture of the world in the eyes of the observer", the connection "ecology-architecture-emotions", "emotional component in the exposition and museum space", "the impact of lighting on emotions caused by architectural space", and "digital recognition of emotions".

Design of recognition algorithm for multiclass digital display instrument based on convolution neural network

Digital display instrument identification is a crucial approach for automating the collection of digital display data. In this study, we propose a digital display area detection CTPNpro algorithm to address the problem of recognizing multiclass digital display instruments. We developed a multiclass digital display instrument recognition algorithm by combining the character recognition network constructed using a convolutional neural network and bidirectional variable-length long short-term memory (LSTM). First, the digital display region detection CTPNpro network framework was designed based on the CTPN network architecture by introducing feature fusion and residual structure. Next, the digital display instrument identification network was constructed based on a convolutional neural network using two-way LSTM and Connectionist temporal classification (CTC) of indefinite length. Finally, an automatic calibration system for digital display instruments was built, and a multiclass digital display instrument dataset was constructed by sampling in the system. We compared the performance of the CTPNpro algorithm with other methods using this dataset to validate the effectiveness and robustness of the proposed algorithm.

Retracted: Digital Image Automatic Recognition and Tracking Based on Electronic Derotation Algorithm

Retracted: Digital Image Automatic Recognition and Tracking Based on Electronic Derotation Algorithm