Field Of Recognition Research Articles

Research on Radionuclide Identification Method Based on GASF and Deep Residual Network

In nuclide identification, traditional methods based on nuclide library comparisons rely on the identification of characteristic peaks, often overlooking the full spectrum information, which leads to cumbersome operations and low efficiency. In recent years, machine learning and deep learning techniques have been introduced into the field of nuclide recognition to improve identification efficiency; however, most existing methods fail to effectively extract deep features from the data. To address this issue, this paper proposes a method that integrates the Gram Angular Summation Field (GASF) algorithm with a Deep Residual Network (ResNet) for processing nuclide energy spectrum data. First, the GASF algorithm is used to transform one-dimensional spectral data into two-dimensional images, thereby fully extracting spatial features from the data. Then, these two-dimensional images are input into the ResNet model, where features are automatically extracted through multiple convolutional layers. Finally, the Softmax layer is used for nuclide classification. Experimental results demonstrate that the proposed method can effectively improve both the accuracy and efficiency of nuclide identification; the recognition accuracy on the simulated data reaches 99.5%, and, when tested with actual measurement data containing unknown radionuclides, the model still achieves a high accuracy of 92.6%. This study shows that the combination of deep learning and signal processing techniques can significantly improve the accuracy and application scope of nuclide identification, offering substantial practical value.

YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7.

Accurate detection and recognition of tea bud images can drive advances in intelligent harvesting machinery for tea gardens and technology for tea bud pests and diseases. In order to realize the recognition and grading of tea buds in a complex multi-density tea garden environment. This paper proposes an improved YOLOv7 object detection algorithm, called YOLOv7-DWS, which focuses on improving the accuracy of tea recognition. First, we make a series of improvements to the YOLOv7 algorithm, including decouple head to replace the head of YOLOv7, to enhance the feature extraction ability of the model and optimize the class decision logic. The problem of simultaneous detection and classification of one-bud-one-leaf and one-bud-two-leaves of tea was solved. Secondly, a new loss function WiseIoU is proposed for the loss function in YOLOv7, which improves the accuracy of the model. Finally, we evaluate different attention mechanisms to enhance the model's focus on key features. The experimental results show that the improved YOLOv7 algorithm has significantly improved over the original algorithm in all evaluation indexes, especially in the (+6.2%) and mAP@0.5 (+7.7%). From the results, the algorithm in this paper helps to provide a new perspective and possibility for the field of tea image recognition.

Pnictogen Bond-Mediated Coassemblies for Noncovalent Molecular Glass.

Pnictogen bond (PnB) occurring on the group-15 elements is recognized as σ- or π-hole-based interaction that has garnered attention in the fields of anion recognition and organocatalysis. Due to the polyvalent feature of pnictogens and high directionality, PnB possesses potential in the design of convergent coassembled materials with acceptors containing lone pair electrons or anions, which however is rarely explored so far. Herein, we unveil the role of antimony (Sb)-based PnB donors in producing self-assembled chiroptical materials with lone pair electron containing acceptors. Steric effect and electronic properties determined the exposure and strength of σ-holes that direct the complexation between components. PnB complexation leads to profound property and self-assembly behavior evolutions compared to the pristine assembly, including crystallinity, photophysical, morphological, and chiroptical properties. The PnB complexes exhibited an accelerated photoisomerization. Ascribed to the multiple σ-holes in Sb donors, amorphous structures were generated, enabling the formation of glassy materials.

Design and development augmented reality using OpenCV for primary education

Children are known to enter a developmental stage between the ages of three and five. It is during this time that they learn how to write letters by tracing them over and making connections between the dots in books. However, this method of involving kids isn't very successful. What if, instead of limiting children to paper and pencil, we allowed them to use the power of air itself to practice writing? Would that bring a magical element to learning? Would it allow children to begin their educational journey? What if education turns into a magical experience that captivates children and turns the ordinary into something fascinating? Computer vision (openCV) with augmented reality (AR). Writing in air has become a evolving yet significant area of research in the field of image processing and pattern recognition. It has led to the development of various applications which have human machine interface. With high quality computers, video cameras and techniques for automatic video analysis, Object tracking has become the most sought out area in the domain of Computer Vision. This study focuses on comparing virtual air canvas built with OpenCV and mediapipe and virtual air canvas built using OpenCV and numpy. Further into the paper, we shall present you our novel idea of integrating Augmented Reality with Computer vision and its impact on teaching and learning.

LiDAR-Based Place Recognition For Autonomous Driving: A Survey

LiDAR has gained popularity in autonomous driving due to advantages like long measurement distance, rich three-dimensional information, and stability in harsh environments. Place Recognition (PR) enables vehicles to identify previously visited locations despite variations in appearance, weather, and viewpoints, even determining their global location within prior maps. This capability is crucial for accurate localization in autonomous driving. Consequently, LiDAR-based Place Recognition (LPR) has emerged as a research hotspot in robotics. However, existing reviews predominantly concentrate on Visual Place Recognition, leaving a gap in systematic reviews on LPR. This article bridges this gap by providing a comprehensive review of LPR methods, thus facilitating and encouraging further research. We commence by exploring the relationship between PR and autonomous driving components. Then, we delve into the problem formulation of LPR, challenges, and relations to previous surveys. Subsequently, we conduct an in-depth review of related research, which offers detailed classifications, strengths and weaknesses, and architectures. Finally, we summarize existing datasets and evaluation metrics and envision promising future directions. This article can serve as a valuable tutorial for newcomers entering the field of place recognition. We plan to maintain an up-to-date project on https://github.com/ShiPC-AI/LPR-Survey .

A Real-Time Posture Detection Algorithm Based on Deep Learning

With the development of machine vision and multimedia technology, posture detection and related algorithms have become widely used in the field of human posture recognition. Traditional video surveillance methods have the disadvantages of slow detection speed, low accuracy, interference from occlusions, and poor real-time performance. This paper proposes a real-time pose detection algorithm based on deep learning, which can effectively perform real-time tracking and detection of single and multiple individuals in different indoor and outdoor environments and at different distances. First, a corresponding pose recognition dataset for complex scenes was created based on the YOLO network. Then, the OpenPose method was used to detect key points of the human body. Finally, the Kalman filter multi-object tracking method was used to predict the state of human targets within the occluded area. Real-time detection of human postures (sitting, stand up, standing, sit down, walking, fall down, and lying down) is achieved with corresponding alarms to ensure the timely detection and processing of emergencies.

Sequence-Specific Minor Groove Binders in Labeling and Single-Molecule Analysis of DNA.

The ability to address specific sequences within DNA is of tremendous interest in biotechnology and biomedicine. Various technologies have been established over the past few decades, such as nicking enzymes and methyltransferase-directed sequence-specific labeling, transcription activator-like effector nucleases (TALENs), the CRISPR-Cas9 system, and polyamides of heterocycles as sequence-specific DNA minor groove binders. Pyrrole-imidazole polyamides have been reported to recognize predetermined DNA sequences, and some successful attempts have demonstrated their potential in regulating gene expression. However, few studies on single-molecule labeling and analysis of DNA have been explored, particularly at single-targeting sites. In this study, we rationally designed and synthesized a set of functional minor groove binders, varying in structures, sequence information addressed, and methods of dye introduction. Their potential for sequence-specific labeling and single-molecule DNA analysis was evaluated through chromatographic and on-surface optical assays. First results indicated that, while they yielded excellent imaging output, the labeling specificity of the hairpin polyamides for single-molecule use was hindered by single-mismatch sites. To address this issue, and in an unprecedented approach, we devised a competitive binding strategy that utilizes ethidium bromide as a nonspecific binder to competitively block the mismatches, significantly enhancing the labeling specificity. These findings provide valuable insights into the use of hairpin polyamides as sequence-programmable and enzyme-free DNA labelers in the field of sequence-specific DNA recognition and modification.

Structural Attributes Injection Is Better: Exploring General Approach for Radar Image ATR with a Attribute Alignment Adapter

Nowadays, deep learning techniques are extensively applied in the field of automatic target recognition (ATR) for radar images. However, existing data-driven approaches frequently ignore prior knowledge of the target, leading to a lack of interpretability and poor performance of trained models. To address this issue, we first integrate the knowledge of structural attributes into the training process of an ATR model, providing both category and structural information at the dataset level. Specifically, we propose a Structural Attribute Injection (SAI) module that can be flexibly inserted into any framework constructed based on neural networks for radar image recognition. Our proposed method can encode the structural attributes to provide structural information and category correlation of the target and can further apply the proposed SAI module to map the structural attributes to something high-dimensional and align them with samples, effectively assisting in target recognition. It should be noted that our proposed SAI module can be regarded as a prior feature enhancement method, which means that it can be inserted into all downstream target recognition methods on the same dataset with only a single training session. We evaluated the proposed method using two types of radar image datasets under the conditions of few and sufficient samples. The experimental results demonstrate that our application of our proposed SAI module can significantly improve the recognition accuracy of the baseline models, which is equivalent to the existing state-of-the-art (SOTA) ATR approaches and outperforms the SOTA approaches in terms of resource consumption. Specifically, with the SAI module, our approach can achieve substantial accuracy improvements of 3.48%, 18.22%, 1.52%, and 15.03% over traditional networks in four scenarios while requiring 1/5 of the parameter count and just 1/14 of the FLOPs on average.

Fractal Analysis of Electrodermal Activity for Emotion Recognition: A Novel Approach Using Detrended Fluctuation Analysis and Wavelet Entropy.

The field of emotion recognition from physiological signals is a growing area of research with significant implications for both mental health monitoring and human-computer interaction. This study introduces a novel approach to detecting emotional states based on fractal analysis of electrodermal activity (EDA) signals. We employed detrended fluctuation analysis (DFA), Hurst exponent estimation, and wavelet entropy calculation to extract fractal features from EDA signals obtained from the CASE dataset, which contains physiological recordings and continuous emotion annotations from 30 participants. The analysis revealed significant differences in fractal features across five emotional states (neutral, amused, bored, relaxed, and scared), particularly those derived from wavelet entropy. A cross-correlation analysis showed robust correlations between fractal features and both the arousal and valence dimensions of emotion, challenging the conventional view of EDA as a predominantly arousal-indicating measure. The application of machine learning for emotion classification using fractal features achieved a leave-one-subject-out accuracy of 84.3% and an F1 score of 0.802, surpassing the performance of previous methods on the same dataset. This study demonstrates the potential of fractal analysis in capturing the intricate, multi-scale dynamics of EDA signals for emotion recognition, opening new avenues for advancing emotion-aware systems and affective computing applications.

MolNexTR: a generalized deep learning model for molecular image recognition

In the field of chemical structure recognition, the task of converting molecular images into machine-readable data formats such as SMILES string stands as a significant challenge, primarily due to the varied drawing styles and conventions prevalent in chemical literature. To bridge this gap, we proposed MolNexTR, a novel image-to-graph deep learning model that collaborates to fuse the strengths of ConvNext, a powerful Convolutional Neural Network variant, and Vision-TRansformer. This integration facilitates a more detailed extraction of both local and global features from molecular images. MolNexTR can predict atoms and bonds simultaneously and understand their layout rules. It also excels at flexibly integrating symbolic chemistry principles to discern chirality and decipher abbreviated structures. We further incorporate a series of advanced algorithms, including an improved data augmentation module, an image contamination module, and a post-processing module for getting the final SMILES output. These modules cooperate to enhance the model’s robustness to diverse styles of molecular images found in real literature. In our test sets, MolNexTR has demonstrated superior performance, achieving an accuracy rate of 81–97%, marking a significant advancement in the domain of molecular structure recognition.Scientific contributionMolNexTR is a novel image-to-graph model that incorporates a unique dual-stream encoder to extract complex molecular image features, and combines chemical rules to predict atoms and bonds while understanding atom and bond layout rules. In addition, it employs a series of novel augmentation algorithms to significantly enhance the robustness and performance of the model.

Facial Detection and Recognition Analysis using Ontology-Driven Machine Learning Model

Facial detection and recognition technologies have achieved remarkable advancements through the integration of ontology-driven machine learning (ML). This study examines how ontology structured framework for representing domain-specific knowledge to enhance the robustness, accuracy, and interpretability of ML models, particularly Convolutional Neural Networks (CNNs), in the field of facial detection and recognition. Acknowledging the limitations of traditional ML methods, such as data inefficiency, inadequate generalization, and insufficient interpretability, this research addresses critical challenges, including semantic discrepancies, variations in environmental conditions, and ethical considerations. By leveraging ontology, the study aims to provide semantic enrichment, contextual adaptation, and data augmentation for ML models. A hybrid methodology is introduced that effectively integrates ontology with CNNs, in conjunction with the Viola-Jones and Eigenfaces algorithms, to improve performance in facial recognition tasks. The study utilizes comprehensive datasets such as CelebA and MegaFace, employing rigorous preprocessing and training processes that incorporate ontology-based feedback mechanisms. The results demonstrated significant improvements in accuracy, robustness, and explainability. Ontology-CNN models outperform traditional approaches in managing variations in facial attributes and environmental conditions. This study concludes that ontology-based frameworks present a promising avenue for developing efficient and ethically responsible facial recognition systems. Future research should focus on exploring the scalability of these models across diverse demographic contexts and further addressing ethical considerations related to privacy and fairness.

Application of FCEEMD-TSMFDE and adaptive CatBoost in fault diagnosis of complex variable condition bearings

The mode mixing problem and inherent mode function selection bias in Fast Ensemble Empirical Mode Decomposition (FEEMD) result in ineffective extraction of fault components during the denoising stage, the loss of coarse-grained information in Multiscale Fuzzy Dispersion Entropy (MFDE) reduces the stability of fault features, and the lack of adaptability of CatBoost hyperparameters leads to reduced diagnostic accuracy. Therefore, a complex variable operating condition fault diagnosis method based on Fast Complementary Ensemble Empirical Mode Decomposition (FCEEMD) - Time-shift Multiscale Fuzzy Dispersion Entropy (TSMFDE) and adaptive Optuna-CatBoost is proposed. We introduce paired white noise with opposite signs in the construction of FCEEMD, effectively suppressing mode aliasing by neutralizing the residual noise generated during decomposition. Then, the Maximum Information Coefficient / Gini Index was introduced to construct a composite screening strategy, retaining the Intrinsic Mode Function (IMF) components that are strongly correlated with the original signal and have a fault impact to reconstruct the denoised signal. Secondly, time-shift multiscale is introduced into the coarse-grained process, and the constructed TSMFDE effectively extracts complete and stable fault features. Finally, with the introduction of the Optuna hyperparameter optimization framework, the adaptive Optuna-CatBoost can accurately diagnose bearing faults. The average fault diagnosis accuracy of the proposed method reached 99.76% and 99.33%, indicating that FCEEMD based on white noise can quickly and accurately decompose non-aliasing vibration modes, and the composite screening strategy can further filter out irrelevant noise modes and improve signal quality; The proposed TSMFDE can extract stable fault features, and its combination with Optuna-CatBoost can further improve the accuracy of fault diagnosis. This model is expected to be applied in more fields of feature extraction and pattern recognition.

Word embedding empowered topic recognition in news articles

Advancements in technology have placed global news at our fingertips, anytime, anywhere, through social media and online news sources. Analyzing the extensive electronic text collections is urgently needed. According to the scholars, combining the topic and word embedding models could improve text representation and help with downstream tasks related to natural language processing. However, the field of news topic recognition lacks a standardized approach to integrating topic models and word embedding models. This presents an exciting opportunity for research, as existing algorithms tend to be overly complex and miss out on the potential benefits of fusion. To overcome limitations in news text topic recognition, this research suggests a new technique word embedding latent Dirichlet allocation that combines topic models and word embeddings for better news topic recognition. This framework seamlessly integrates probabilistic topic modeling using latent Dirichlet allocation with Gibbs sampling, semantic insights from Word2Vec embeddings, and syntactic relationships to extract comprehensive text representations. Popular classifiers leverage these representations to perform automatic and precise news topic identification. Consequently, our framework seamlessly integrates document-topic relationships and contextual information, enabling superior performance, enhanced expressiveness, and efficient dimensionality reduction. Our word embedding method significantly outperforms existing approaches, reaching 88% and 97% accuracy on 20NewsGroup and BBC News in news topic recognition.

A Survey of Multi-modal Emotion Recognition Based on Deep Learning

Multi-modal emotion recognition technology explores emotion recognition by integrating facial expression, voice intonation, text analysis and other multi-source data, so as to improve the naturalness and accuracy of human-computer interaction. Aiming at the emerging field of multi-modal emotion recognition, this paper introduces three single-modal emotion recognition methods of text, face and voice, especially the problem of multi-modal emotion fusion, and introduces the methods with high success rate of multi-modal emotion fusion recognition in recent years. Through comparative analysis, the conclusion is drawn that the current fusion methods are more complicated and the fusion success rate has been improved to some extent. However, the number of data sets on multi-modal emotion analysis is small, and the research on gesture and other modes of emotion recognition is also scarce. In the later stage, it is necessary to enrich the data set and add new modes to improve the accuracy and robustness of the multi-modal emotion recognition and analysis system.

The relational model of sense of coherence: explaining refugees’ mental health and well-being in Austria

Purpose This paper aims to construct a model explaining migrant health and well-being from a salutogenic perspective. Accounting for the relational, interactional factors impacting on the health of forced migrants, the “Relational Model of Sense of Coherence” combines elements from Antonovsky’s theory of salutogenesis with elements from Honneth’s theory of recognition. Design/methodology/approach The model has been developed from the empirical findings of a two-year qualitative study with 28 forced migrants in Austria. Besides initial and final surveys on the participants’ perception of health, health literacy and participation, data were gathered in a qualitative, participatory action research setting and analysed by the method of interpretative case reconstruction. The model is applied to the case reconstruction of a female refugee from Iraq explaining the dimensions impacting on her self-perceived status of health and well-being. Findings Next to consistency/comprehensibility and load balance/manageability persons need to experience participation/controllability as well as relatedness/self-confidence, recognition of rights/self-respect and social recognition/self-esteem to develop and/or maintain a strong, relational sense of coherence. All six dimensions contribute to feelings of meaningfulness; all components are necessary for a move towards the healthy end of the health-ease/dis-ease continuum. Originality/value The paper contributes to theory building in the fields of salutogenesis and recognition by developing a model based on an in-depth, participatory qualitative study with a vulnerable target group.

Motion-deblurring ghost imaging for an axially moving target.

For lensless ghost imaging (GI) with thermal light, the axially relative motion constrained in the range of the system's depth of focus (DOF) can still cause image blurring because of a variable magnification. We propose a motion-deblurring GI system with pseudo-thermal light, which can overcome the resolution degradation caused by the axial motion. Both the analytical and experimental results demonstrate that high-resolution GI can be always obtained as long as the target's random motion range is smaller than the system's DOF, without using the prior information of motion estimation. We also show that the system's DOF can be extended by optimizing the geometrical shape of the laser spot on the rotating ground glass disk (RGGD). The imaging performance comparison between the proposed GI system and the corresponding lensless GI system is also discussed. This technique can promote the practical application of GI in the field of moving-target detection and recognition.

Research on Emotion Recognition Algorithm of Piano Music Based on Multimodal Learning

The purpose of this study is to propose an emotion recognition algorithm for piano music based on multimodal learning. Multi-modal learning is a learning method that combines various types of data. By combining different modal information, learning tasks can be completed more comprehensively and accurately. In the field of music emotion recognition, multimodal learning can extract the emotional features of music from different angles, and improve the recognition accuracy and robustness. In this study, the multi-modal learning method is mainly used, and the representative features are extracted by combining the audio signal, score information and the performance of the piano music, and the machine learning algorithm is used to classify the emotions. The audio signal is preprocessed, including noise reduction, cutting and other operations, and then the features of the audio signal are obtained by feature extraction methods, such as short-time Fourier transform (STFT) and formant analysis (RPA). Digitally convert the score, extract the structure, melody, harmony and other characteristics of the music, and obtain the emotional information of the music by analyzing the relationship between symbols and notes in the score. By analyzing the performance skills, strength, speed and other parameters of the player, the characteristics related to the emotional expression of the player are extracted. Machine learning algorithm is used to train and classify the fusion features, and the emotion recognition of piano music is realized. In this study, the emotion recognition algorithm of piano music based on multimodal learning can mine the emotion information of music at different levels, improve the accuracy and robustness of emotion recognition, and provide useful reference for the field of music emotion calculation.

Enhancing neural network applications in phonetic classification through population-based incremental learning

Significant progress has been achieved in the field of Automatic Speech Recognition (ASR) thanks to the development of powerful algorithms. Research based on simplified biological models has led to the emergence of a new class called Estimation of Distribution Algorithms (EDA), which preserves significant partial solutions. Population-Based Incremental Learning (PBIL) is a technique that combines stochastic search and optimization. It is a statistical approach with evolutionary computation similar to EDAs, aimed at adapting recognition systems based on artificial Neural Networks (NN). Our main contribution lies in the improvement achieved by PBIL, which outperforms Genetic Algorithms (GA) by 16% and Evolutionary Strategies (ES) by 9.93%.

Developing Innovative Feature Extraction Techniques from the Emotion Recognition Field on Motor Imagery Using Brain–Computer Interface EEG Signals

Research on brain–computer interfaces (BCIs) advances the way scientists understand how the human brain functions. The BCI system, which is based on the use of electroencephalography (EEG) signals to detect motor imagery (MI) tasks, enables opportunities for various applications in stroke rehabilitation, neuroprosthetic devices, and communication tools. BCIs can also be used in emotion recognition (ER) research to depict the sophistication of human emotions by improving mental health monitoring, human–computer interactions, and neuromarketing. To address the low accuracy of MI-BCI, which is a key issue faced by researchers, this study employs a new approach that has been proven to have the potential to enhance motor imagery classification accuracy. The basic idea behind the approach is to apply feature extraction methods from the field of emotion recognition to the field of motor imagery. Six feature sets and four classifiers were explored using four MI classes (left and right hands, both feet, and tongue) from the BCI Competition IV 2a dataset. Statistical, wavelet analysis, Hjorth parameters, higher-order spectra, fractal dimensions (Katz, Higuchi, and Petrosian), and a five-dimensional combination of all five feature sets were implemented. GSVM, CART, LinearSVM, and SVM with polynomial kernel classifiers were considered. Our findings show that 3D fractal dimensions predominantly outperform all other feature sets, specifically during LinearSVM classification, accomplishing nearly 79.1% mean accuracy, superior to the state-of-the-art results obtained from the referenced MI paper, where CSP reached 73.7% and Riemannian methods reached 75.5%. It even performs as well as the latest TWSB method, which also reached approximately 79.1%. These outcomes emphasize that the new hybrid approach in the motor imagery/emotion recognition field improves classification accuracy when applied to motor imagery EEG signals, thus enhancing MI-BCI performance.

Comparing human-labeled and AI-labeled speech datasets for TTS

As the output quality of neural networks in the fields of automatic speech recognition (ASR) and text-to-speech (TTS) continues to improve, new opportunities are becoming available to train models in a weakly supervised fashion, thus minimizing the manual effort required to annotate new audio data for supervised training. While weak supervision has recently shown very promising results in the domain of ASR, speech synthesis has not yet been thoroughly investigated regarding this technique despite requiring the equivalent training dataset structure of aligned audio-transcript pairs. In this work, we compare the performance of TTS models trained using a well-curated and manually labeled training dataset to others trained on the same audio data with text labels generated using both grapheme- and phoneme-based ASR models. Phoneme-based approaches seem especially promising, since even for wrongly predicted phonemes, the resulting word is more likely to sound similar to the originally spoken word than for grapheme-based predictions. For evaluation and ranking, we generate synthesized audio outputs from all previously trained models using input texts sourced from a selection of speech recognition datasets covering a wide range of application domains. These synthesized outputs are subsequently fed into multiple state-of-the-art ASR models with their output text predictions being compared to the initial TTS model input texts. This comparison enables an objective assessment of the intelligibility of the audio outputs from all TTS models, by utilizing metrics like word error rate and character error rate. Our results not only show that models trained on data generated with weak supervision achieve comparable quality to models trained on manually labeled datasets, but can outperform the latter, even for small, well-curated speech datasets. These findings suggest that the future creation of labeled datasets for supervised training of TTS models may not require any manual annotation but can be fully automated.