Joint Recognition Research Articles

Вільний рух товарів: моніторинг та оцінка впровадження угоди «Про асоціацію між Україною та ЄС

Abstract. The article analyses and assesses the current state of Ukraine's implementation of the EU acquis under the Association Agreement in the sector ‘Trade and Trade-related Matters’ on free movement of goods. The legislative and institutional framework for free movement of goods, albeit partially, already exists, in particular for the sectors that the ACAA may cover, thanks to the DCFTA commitments. Currently, the Verkhovna Rada of Ukraine is considering several draft laws on state market surveillance and standardisation to enable Ukraine to become a full member of the EU customs union in the near future. It is noted that the rapid elimination of systemic problems and further adoption of horizontal and vertical legislation of Ukraine harmonised with the EU law on free movement of goods will allow to move the issue of signing the Agreement on Joint Recognition of Certificates of Conformity for Industrial Products by Ukraine and the European Union (ACAA) into the practical plane. Monitoring of the fulfilment of obligations in this area made it possible to conclude that the level of preparation for bringing domestic trade legislation in key sectors in line with the European acquis communautaireis average . The articleidentifies the measures used to formulate and implement the policy of free movement of goods to ensure the fulfilment of Ukraine's obligations under the EU-Ukraine Association Agreement. It is concluded that our country demonstrates a moderate level of preparation in the field of free movement of goods, which, on the basis of common rules and procedures, guarantees the possibility of free trade in goods to the Common Market member states in the European Union. At the same time, Ukraine still needs to analyse its legislation, especially in terms of its practical application in this area, and do its homework, in particular, on technical regulations, standards, conformity assessment, accreditation, metrology and market surveillance. Keywords: free movement of goods; Association Agreement; ACAA Agreement; EU acquis; EU internal market; Deep and Comprehensive Free Trade Area (DCFTA); customs union.

Real-time joint recognition of weather and ground surface conditions by a multi-task deep network

Climate change and the occurrence of intense and unexpected weather events highlighted the need for real-time weather warning systems, especially in smart roads and isolated scenarios like rural areas. In this work, we propose to jointly recognize the weather and the ground surface conditions using existing video surveillance systems. Previous works separately tackled these two tasks even if they are correlated to each other. We propose a convolutional neural network with shared weights in the lower layers and two separate classification branches on top to exploit the correlation between the tasks and, at the same time, learn diverse high-level features for each task. Moreover, the network architecture implements attention mechanisms allowing the classification branches to focus on diverse image regions. The method is versatile and allows us to train the network on partially labeled data. The experimental analysis on real data demonstrate the effectiveness of the proposed method on both tasks, confirmed by the accuracy comparison with existing methods for the recognition of weather and ground surface conditions. The multi-task solution improves the inference speed (50 frames per second) and reduces the required memory (less than 1 GB) with respect to a system with two different single-task approaches; these results confirm that the proposed solution is ready for video surveillance applications to support smart cities.

Detecting emerald ash borer boring vibrations using an encoder-decoder and improved DenseNet model.

Forest ecosystems are under constant threat from wood-boring pests such as the Emerald ash borer (EAB), which remain elusive owing to their hidden life cycles within tree trunks. Early detection is vital to mitigate economic and ecological damage. The main current monitoring method is manual detection which is ineffective at early stages of infestation. This study introduces VibroEABNet, a deep learning-based joint recognition network designed to enhance the detection of EAB boring vibration signals, with a novel approach integrating denoising and recognition modules. The proposed VibroEABNet model demonstrated exceptional performance, achieving an average accuracy of 98.98% across multiple signal-to-noise ratios (SNRs) in test datasets and a remarkable 97.5% accuracy in real forest datasets, surpassing traditional models and other deep learning networks evaluated in this study. These findings were supported by rigorous noise resistance analysis and real dataset evaluation, indicating the model's robustness and reliability in practical applications. Furthermore, the model's efficiency was highlighted by its inference time of 26 ms and a compact model size of 8.43 MB, underscoring its suitability for deployment in resource-limited environments. The development of VibroEABNet marks a significant advancement in pest detection methodologies, offering a scalable, accurate and efficient solution for early monitoring of wood-boring pests. The integration of a denoising module within the network structure addresses the challenge of environmental noise, one of the primary limitations in acoustic monitoring of pests. Currently, this research is limited to a specific pest. Future work will focus on the applicability of this network to other wood-boring pests. © 2024 Society of Chemical Industry.

Retraction Note: Accuracy evaluation of sports training actions based on grating ruler displacement sensor and joint recognition algorithm

Retraction Note: Accuracy evaluation of sports training actions based on grating ruler displacement sensor and joint recognition algorithm

An Automatic Method for Elbow Joint Recognition, Segmentation and Reconstruction.

Elbow computerized tomography (CT) scans have been widely applied for describing elbow morphology. To enhance the objectivity and efficiency of clinical diagnosis, an automatic method to recognize, segment, and reconstruct elbow joint bones is proposed in this study. The method involves three steps: initially, the humerus, ulna, and radius are automatically recognized based on the anatomical features of the elbow joint, and the prompt boxes are generated. Subsequently, elbow MedSAM is obtained through transfer learning, which accurately segments the CT images by integrating the prompt boxes. After that, hole-filling and object reclassification steps are executed to refine the mask. Finally, three-dimensional (3D) reconstruction is conducted seamlessly using the marching cube algorithm. To validate the reliability and accuracy of the method, the images were compared to the masks labeled by senior surgeons. Quantitative evaluation of segmentation results revealed median intersection over union (IoU) values of 0.963, 0.959, and 0.950 for the humerus, ulna, and radius, respectively. Additionally, the reconstructed surface errors were measured at 1.127, 1.523, and 2.062 mm, respectively. Consequently, the automatic elbow reconstruction method demonstrates promising capabilities in clinical diagnosis, preoperative planning, and intraoperative navigation for elbow joint diseases.

Joint recognition for location and activity based on multidimensional features of CSI images

Joint recognition for location and activity based on multidimensional features of CSI images

Multi-LiDAR human joint recognition algorithm in hospital wards based on improved V2V-Posenet

To prevent convulsions and falls of patients in the absence of medical staff, it is crucial to monitor their physical condition in hospital wards. However, several unresolved challenges in human joint recognition remain, such as object occlusion, human self-occlusion and complex backgrounds, resulting in difficulties in its practical application. In this paper, a multi-LiDAR system is proposed to obtain a multi-view human body point cloud. An improved V2V-Posenet model was introduced to detect the actual position of the human joint. In this system, each point cloud was spliced into a full point cloud and voxelized into the model. We also used a random voxel zero setting for data enhancement, constraining the relative length between human joints into a loss function and three-dimensional Gaussian filtering in a heat map for model learning. The improved model exhibited excellent performance in detecting human joints in hospital wards. The experimental results showed that the improved model achieved 91.6 % mean average precision, compared to 80.1 % for the original model and 77.4 % for the comparison algorithm A2J-Posenet. The speed of the improved model meets the requirements for real-time target detection.

RETRACTED ARTICLE: Accuracy evaluation of sports training actions based on grating ruler displacement sensor and joint recognition algorithm

RETRACTED ARTICLE: Accuracy evaluation of sports training actions based on grating ruler displacement sensor and joint recognition algorithm

Self-Adaptive Representation Learning Model for Multi-Modal Sentiment and Sarcasm Joint Analysis

Sentiment and sarcasm are intimate and complex, as sarcasm often deliberately elicits an emotional response in order to achieve its specific purpose. Current challenges in multi-modal sentiment and sarcasm joint detection mainly include multi-modal representation fusion and the modeling of the intrinsic relationship between sentiment and sarcasm. To address these challenges, we propose a single-input stream self-adaptive representation learning model (SRLM) for sentiment and sarcasm joint recognition. Specifically, we divide the image into blocks to learn its serialized features and fuse textual feature as input to the target model. Then, we introduce an adaptive representation learning network using a gated network approach for sarcasm and sentiment classification. In this framework, each task is equipped with its dedicated expert network responsible for learning task-specific information, while the shared expert knowledge is acquired and weighted through the gating network. Finally, comprehensive experiments conducted on two publicly available datasets, namely Memotion and MUStARD, demonstrate the effectiveness of the proposed model when compared to state-of-the-art baselines. The results reveal a notable improvement on the performance of sentiment and sarcasm tasks.

Real-time monitoring of the corrosion behaviour of the 304SS in HCl solution using BPNN with joint image recognition and electrochemical noise

Electrochemical noise has an important reference role in the study of early corrosion; however, a direct correlation between the microscopic morphology and the electrochemical noise of the corrosion process is lacking. This study uses a back propagation artificial neural network (BPNN) optimized by three intelligent optimization algorithms to real-time monitor the local corrosion of 304 stainless steel in HCl solution with joint recognition and feature extraction of corrosion images and electrochemical noise. The results show that the corrosion monitoring model established by optimized BPNN with genetic algorithms exhibits the highest convergence speed and accuracy.

EEG-Based Evaluation of Aesthetic Experience Using BiLSTM Network

Evaluation of aesthetic design fulfills a pivotal function in product development, which urges for an efficacious objective method to measure customers’ experience. The stability and effectiveness of electroencephalography (EEG) make it a suitable tool for aesthetic experience measurement. Nevertheless, existing studies have several limitations, especially regarding the stimuli and the algorithm. The potential of an EEG-based deep learning model has not been verified in pinpointing subtle differences in physical product aesthetics. To fill the research gap in this issue, we recorded EEG signals in real-life scenarios when participants were presented with different types of physical smartphones, and asked participants to rate them from four dimensions of aesthetic experience (arousal, valence, likeness, and aesthetic evaluation). Then, the time–frequency data were fed into a spatial feature extraction network and an attention-based bidirectional long short-term memory (BiLSTM) optimized by the cross-entropy loss function. The result showed that at 16s window size, the four outcome models yielded the best joint recognition performance of aesthetic experience with an average accuracy of over 85% (arousal: 88.10%, valence: 87.97%, likeness: 85.99%, and aesthetic evaluation: 87.23%). It provides an objective cross-subject recognition method with multi-faceted evaluation results of aesthetic experience. Additionally, we verified the ability of EEG as a reliable and informative resource in terms of aesthetic experience evaluation, even with subtle differences. More practically, a future direction of incorporating EEG signals into subjective product aesthetics measurement could be given more credit.

Joint recognition of basic and compound facial expressions by mining latent soft labels

Previous works on facial expression recognition focus on basic emotions, while ignoring more complex compound expressions. However, both basic and compound emotions appear in the real-world environment. In this work, we aim to jointly recognize basic and compound expressions. Aiming at the Basic-Compound Facial Expression Recognition (BC-FER) task, we illustrate that traditional hard label training is not ideal due to great label dependencies. Therefore, we propose an expression soft label mining (ESLM) method to improve the performance. On the one hand, an iterated soft label mining (ISLM) algorithm assisted by teacher–student network is proposed to make the network generate soft targets automatically for learning. On the other hand, to explicitly leverage prior knowledge of label correlations, we propose an expression correlation score learning (ECSL) loss to regularize the predicted distributions. Extensive experimental results on CFEE, RAF-DB, and EmotioNet show that our method achieves state-of-the-art performance on BC-FER task.

White capitalism within communities of craftivism: mask making and health maintenance disparities during COVID-19

When lockdown started, my anxiety kept me on a tight string—I (author 1) remember drowning in intense, omnipresent agitation as I used every “extra” moment I could to research mask styles, adapt patterns published online or distributed by different organizations to increase access to masks for better functionality, and distribute masks to those who needed them via an old ice cream bucket on my front bench. Yet, I recognized that the time I used, my ability to quarantine and so much more contributed to my privilege in doing so. I (author 2) had no masks on hand, so after watching a few tutorials online, I concocted my own makeshift mask. Not only did my MacGyvered creation not fit properly, it was superhot and lacked sufficient air flow due to the thickness of the fabric. Although this initial mask-making strategy wasn't very practical, I recognized the importance of having not only a mask but one that would fit such that it properly served its purpose: to preserve my health. By fashioning a collaborative, autoethnographic approach to understanding craftivism during the 2020 coronavirus crisis, from a Black scholar doing disparities and equity focused health communication work and a white scholar engaging activist rhetorics and digital media equity scholarship, our joint recognition of economic and infrastructural privilege offered understanding of how forms of pattern design (techne) and cultural community infrastructure influenced our maker agencies and constraints. Reflecting on our immersive mask-making experiences, we recognized a value of creating alternative economic structures, yet also unmasked significant racial agencies within craftivist communities which required cultural historic materiality and knowledge, time to create and revise, networked access, and physical risk. Here, we offer insight into how a crisis revealed systemic biases as agency to reorient ourselves toward anti-racist processes and practices.

Intelligent recognition of joints and fissures in tunnel faces using an improved mask region‐based convolutional neural network algorithm

AbstractTo address the challenges of low recognition accuracy, low robustness, and low detection efficiency in existing tunnel face joint and fissure recognition methods, we present a deep learning recognition segmentation algorithm called the mask region convolutional neural network (Mask R‐CNN) that is enhanced by an advanced Transformer attention mechanism and deformable convolution network (Mask R‐CNN‐TD). The Transformer attention mechanism improves the backbone network's ability to extract image features by focusing on important areas. A deformable convolutional network enables the network to more precisely conform to the morphological characteristics of joints and fissures on the tunnel face, thereby enhancing the accuracy of detection. Experimental results demonstrate that Mask R‐CNN‐TD achieves superior performance, compared to Mask R‐CNN series algorithms and other instance segmentation methods in terms of detection accuracy, with mean average precision scores of 70.5%, 70.8%, 53.2%, and 63.3% for detection box and mask segmentation at thresholds of 0.5 and 0.75, respectively. Based on the stable and efficient Mask R‐CNN‐TD model, we developed a mobile application called tunnel face detector to automatically detect tunnel faces on the construction site.

Two-Step Identification Method and Experimental Verification of Weld Damage at Joints in Spatial Grid Structures

Welded joints in grid structures are susceptible to damage and destruction when exposed to random excitation. The complexity of the grid structure poses challenges for realizing the damage recognition of welded joints. In this study, a two-step method is proposed specifically for damage identification of welded joints in grid structures, combining wavelet analysis and fuzzy pattern recognition to accurately identify the location and extent of damage in welded joints. Firstly, the structure is divided based on the analysis of the influence range of joint damage. Key joints are selected within the sub-regions where sensors are installed, and the acceleration response of these key joints is measured. Wavelet analysis is then applied to identify the sub-regions where weld damage occurs. Secondly, an equivalent finite element model is established for joints with varying degrees of damage. The damage index, calculated as the ratio of the absolute value of the difference in the first-order element strain mode of the members, increases with the degree of damage during joint weld damage. By monitoring the changes in the damage index of sensitive members, which exhibit significant changes with varying weld damage degrees, a damage pattern database is constructed for each sub-region. The membership degree between joint damage and the patterns in the pattern database is then calculated to determine the location and degree of weld damage. To validate the effectiveness of the proposed method, an experiment was conducted using a grid structure model with replaceable members. Highly sensitive FBG sensors were designed to measure the acceleration response of the joints, resulting in accurate identification of damaged sub-regions solely through the measurement of key joint acceleration responses. Furthermore, within the damaged sub-regions, the fuzzy pattern recognition method precisely determined the location and degree of weld damage in the joints. The experimental results demonstrate that the proposed method effectively reduces the complexity of the structure by dividing the grid structure into sub-regions, and enables the two-step identification method to achieve successful damage identification for the joints in the grid structure with high efficiency and accuracy.

Multi-domain-fusion deep learning for automatic modulation recognition in spatial cognitive radio

Automatic modulation recognition (AMR) is a critical technology in spatial cognitive radio (SCR), and building high-performance AMR model can achieve high classification accuracy of signals. AMR is a classification problem essentially, and deep learning has achieved excellent performance in various classification tasks. In recent years, joint recognition of multiple networks has become increasingly popular. In complex wireless environments, there are multiple signal types and diversity of characteristics between different signals. Also, the existence of multiple interference in wireless environment makes the signal characteristics more complex. It is difficult for a single network to accurately extract the unique features of all signals and achieve accurate classification. So, this article proposes a time–frequency domain joint recognition model that combines two deep learning networks (DLNs), to achieve higher accuracy AMR. A DLN named MCLDNN (multi-channel convolutional long short-term deep neural network) is trained on samples composed of in-phase and quadrature component (IQ) signals, to distinguish modulation modes that are relatively easy to identify. This paper proposes a BiGRU3 (three-layer bidirectional gated recurrent unit) network based on FFT as the second DLN. For signals with significant similarity in the time domain and significant differences in the frequency domain that are difficult to distinguish by the former DLN, such as AM-DSB and WBFM, FFT (Fast Fourier Transform) is used to obtain frequency domain amplitude and phase (FDAP) information. Experiments have shown that the BiGUR3 network has superior extraction performance for amplitude spectrum and phase spectrum features. Experiments are conducted on two publicly available datasets, the RML2016.10a and RML2016.10b, and the results show that the overall recognition accuracy of the proposed joint model reaches 94.94% and 96.69%, respectively. Compared to a single network, the recognition accuracy is significantly improved. At the same time, the recognition accuracy of AM-DSB and WBFM signals has been improved by 17% and 18.2%, respectively.

Joint recognition of text and layout in historical Russian documents

Joint recognition of text and layout in historical Russian documents

Joint recognition and parameter estimation of cognitive radar work modes with LSTM-transformer

The recent developed cognitive radars can implement flexible work modes with programmable modulation types and optimized modulating values for each mode definition parameter. Automatic analysis of these work modes is a significant challenge for modern electromagnetic reconnaissance receivers. In this paper, a Multi-Output Multi-Structure (MOMS) learning-based processing framework is proposed for Joint inter-pulse automatic Modulation Recognition and Parameter Estimation (JMRPE-MOMS). We propose a label construction method as a feature interpretation method of the network to facilitate MOMS learning and utilize the correlations between labels for performance gain. Moreover, an LSTM-Transformer is designed to mine deep time-series characteristics, which can model local and global relationships and reduce quantization loss. The proposed framework can perform joint modulation recognition and parameter estimation (JMRPE) tasks simultaneously with flexible output structures including scalar output and vector output with fixed or variable sizes. Extensive simulations are performed based on the simulated radar work modes defined with pulse repetition interval (PRI) sequences. The simulation results validate the effectiveness and superiority of the proposed method especially under non-ideal electromagnetic environments.

Working Mode Recognition of Non-Specific Radar Based on ResNet-SVM Learning Framework.

Mode recognition is a basic task to interpret the behavior of multi-functional radar. The existing methods need to train complex and huge neural networks to improve the recognition ability, and it is difficult to deal with the mismatch between the training set and the test set. In this paper, a learning framework based on residual neural network (ResNet) and support vector machine (SVM) is designed, to solve the problem of mode recognition for non-specific radar, called multi-source joint recognition framework (MSJR). The key idea of the framework is to embed the prior knowledge of radar mode into the machine learning model, and combine the manual intervention and automatic extraction of features. The model can purposefully learn the feature representation of the signal on the working mode, which weakens the impact brought by the mismatch between training and test data. In order to solve the problem of difficult recognition under signal defect conditions, a two-stage cascade training method is designed, to give full play to the data representation ability of ResNet and the high-dimensional feature classification ability of SVM. Experiments show that the average recognition rate of the proposed model, with embedded radar knowledge, is improved by 33.7% compared with the purely data-driven model. Compared with other similar state-of-the-art reported models, such as AlexNet, VGGNet, LeNet, ResNet, and ConvNet, the recognition rate is increased by 12%. Under the condition of 0-35% leaky pulses in the independent test set, MSJR still has a recognition rate of more than 90%, which also proves its effectiveness and robustness in the recognition of unknown signals with similar semantic characteristics.

건물 열쾌적 제어를 위한 다중 재실자 대상 활동량 산출모델 성능평가

Purpose: The purpose of this study is to evaluate applicability of a model that can estimate MET in real time for multiple occupants as well as single occupants for application of PMV-based control in building environments. Method: Based on joint recognition stage and activity classification stage, a model that can estimate MET of multiple occupants from indoor images was proposed. Pose image dataset collected from the internet and self-captured in the lab was used for model training. For the performance evaluation of the model in single and multiple occupants condition, experiments were conducted in a test-bed on three activities; sitting, standing, and walking. The model was evaluated with the accuracy of real-time activity classification and representative MET estimation which was most frequent value in a given period of time. Result: The real-time activity classification accuracy of single occupant for the three activities was high in the order of sitting, standing, and walking. The representative MET estimation accuracy of single occupant applying the 1-min frequent value was 100% for all three activities. The representative MET estimation for multiple occupants showed an average accuracy of 88.8% in 1-min frequent and 100% accuracy in 5-min frequent. The result confirmed that the proposed model can be applied in the actual environment, when applying the representative MET value to multiple occupants.