Recognition Model Research Articles

Neural networks for abstraction and reasoning

For half a century, artificial intelligence research has attempted to reproduce the human qualities of abstraction and reasoning - creating computer systems that can learn new concepts from a minimal set of examples, in settings where humans find this easy. While specific neural networks are able to solve an impressive range of problems, broad generalisation to situations outside their training data has proved elusive. In this work, we look at several novel approaches for solving the ion & Reasoning Corpus (ARC). This is a dataset of abstract visual reasoning tasks introduced to test algorithms on broad generalization. Despite three international competitions with $100,000 in prizes, the best algorithms still fail to solve a majority of ARC tasks. The best solvers today rely on complex hand-crafted rules, without using machine learning at all. We revisit whether recent advances in neural networks allow progress on this task, or whether an entirely different class of models are required. First, we adapt the DreamCoder neurosymbolic reasoning solver to ARC. DreamCoder automatically writes programs in a bespoke domain-specific language to perform reasoning, using a neural network to mimic human intuition. We present the Perceptual ion and Reasoning Language (PeARL) language, which allows DreamCoder to solve ARC tasks, and propose a new recognition model that allows us to significantly improve on the previous best implementation. We also propose a new encoding and augmentation scheme that allows large language models (LLMs) to solve ARC tasks, and find that the largest models can solve some ARC tasks. LLMs are able to solve a different group of problems to state-of-the-art solvers, and provide an interesting way to complement other approaches. We perform an ensemble analysis, combining systems to achieve better results than any system alone and analysing individual strengths. However, it is sobering to see that approaches based on neural networks still lag behind existing hand-crafted solvers, and we suggest avenues for future improvements. Our findings with the ensemble model may indicate that a diversity of methods might be necessary to solve problems in ARC. Humans likely employ diverse strategies to solve ARC. Studies involving human participants to identify the strategies they employ to solve ARC could provide valuable insights for future AI approaches. Finally, we publish the arckit Python library to make future research on ARC easier.

Multi-image transmission based on a multi-channel OAM-array-coded optical communication system using a designed Dammann grating and an integrated vortex grating.

Vortex beams (VBs) have the potential to support high-capacity optical communications. However, a typical VB carries only a single orbital angular momentum (OAM) in space, limiting its high-capacity communication. We propose controllably simultaneous generation of high-quality VB arrays with multiple OAMs, creating the independent multi-channel space in which the OAM mode can be flexibly manipulated at the corresponding spatial location. We then demonstrate a VB array-based multi-channel optical communication system combining a custom-designed Dammam grating and an integrated vortex grating, with the help of a designed single-input multiple-output deep learning recognition model. Experimental demonstration of the simultaneous transmission of four grayscale images was verified, with an average error rate of less than 0.003 without turbulence and 0.061 with turbulence. The proposed multi-channel method (multi-image transmission) can significantly increase the versatility of the VB array and further broaden its application in high-capacity optical communications.

Remoscope: a label-free imaging cytometer for malaria diagnostics.

Malaria diagnostic testing in high transmission settings remains a burden on healthcare systems. Here we present Remoscope, a portable automated imaging cytometer that scans fresh, unstained whole blood using a custom neural network on low-cost hardware. By screening up to two million red blood cells, Remoscope performs label-free quantitative stage-specific detection of Plasmodium falciparum ( Pf ) in 1-12 minutes without sample fixation, staining, or slide scanning. Flow is used to achieve high cellular throughput, with blood confined to a 4.5 µm monolayer in low-cost disposable flow cartridges. Remoscope performance was benchmarked in vitro by titration of cultured parasites into uninfected whole blood at concentrations of 17.1-710,000 parasites/µL. Counts generated by Remoscope demonstrated a linear response across the entire range. Considering drug susceptibility assays, the half-maximal effective concentration (EC50) of chloroquine (CQ) for the W2 strain of Pf was 211 nM by Remoscope, compared to 191 nM for conventional flow cytometry. Remoscope's real-world diagnostic accuracy was evaluated in a cohort of 500 individuals in eastern Uganda, comprising 601 unique clinic visits. Parallel measurements of parasitemia were performed using Remoscope, qPCR targeting the multicopy conserved var gene acidic terminal sequence, and microscopic evaluation of Giemsa-stained thick blood smears. Remoscope's limit of detection with respect to qPCR was 95.1 parasites/µL. At this threshold, the system had a sensitivity of 83%, specificity of 96%, Positive Predictive Value (PPV) of 91%, and a Negative Predictive Value (NPV) of 93%. Remoscope's speed, accuracy, low cost, and ease of use address practical challenges in malaria diagnostic settings around the world. As a general imaging flow cytometer, Remoscope may also inform the development of recognition models for the diagnosis of other infectious and noninfectious blood disorders.

PSATF-6mA: an integrated learning fusion feature-encoded DNA-6mA methylcytosine modification site recognition model based on attentional mechanisms.

DNA methylation is of crucial importance for biological genetic expression, such as biological cell differentiation and cellular tumours. The identification of DNA-6mA sites using traditional biological experimental methods requires more cumbersome steps and a large amount of time. The advent of neural network technology has facilitated the identification of 6mA sites on cross-species DNA with enhanced efficacy. Nevertheless, the majority of contemporary neural network models for identifying 6mA sites prioritize the design of the identification model, with comparatively limited research conducted on the statistically significant DNA sequence itself. Consequently, this paper will focus on the statistical strategy of DNA double-stranded features, utilising the multi-head self-attention mechanism in neural networks applied to DNA position probabilistic relationships. Furthermore, a new recognition model, PSATF-6mA, will be constructed by continually adjusting the attentional tendency of feature fusion through an integrated learning framework. The experimental results, obtained through cross-validation with cross-species data, demonstrate that the PSATF-6mA model outperforms the baseline model. The in-Matthews correlation coefficient (MCC) for the cross-species dataset of rice and m. musus genomes can reach a score of 0.982. The present model is expected to assist biologists in more accurately identifying 6mA locus and in formulating new testable biological hypotheses.

Multisensory Integration in Lexical Processing: Predicting Word Recognition Through Cross-Modal Capability

The integration of multisensory in lexical processing has garnered significant interest in cognitive linguistics and psycholinguistics. This study investigates the predictive power of cross-modal capability (CMC) on word recognition, focusing on how sensory integration influences cognitive processing and lexical decision-making. By collecting five-sense ratings for synesthetic adjectives, we computed the cross-modal capability for each word. We then conducted regression analyses to examine the relationship between these indices and reaction time in lexical decision tasks. Our findings reveal that words with higher cross-modal capabilities, as measured by CMC, are recognized and processed more quickly. This superior predictive power of CMC underscores the importance of sensory associations in lexical processing and highlights the need for comprehensive indices that account for multiple sensory inputs. These results provide deeper insights into the cognitive mechanisms underlying word recognition and processing speed, suggesting that CMC is a better independent variable for partially predict lexical cognition and recognition. This research contributes to our understanding of multisensory integration in lexical processing and has implications for models of word recognition and cognitive linguistics.

Combined LinkNet-MBi-LSTM for brain activity recognition with new Stockwell transform features.

Recognizing brain activity from EEG waves is an important field of study in biomedical engineering and neuroscience. Conventional approaches usually begin with signal processing techniques to extract features from the EEG data, and then machine learning algorithms are applied to classify the data. However, the spatial resolution of these EEG signals is low, which makes it difficult to pinpoint the exact location of the neural activity source in the brain. There are ongoing initiatives to use DL-based brain activity recognition algorithms to overcome these constraints. Therefore, this work presents a novel hybrid framework for brain activity detection using the enhanced Stockwell transform and an EEG signal that is called LinkNet and modified bidirectional-long short-term memory (LN-MBi-LSTM) model. This framework follows a methodical approach that includes stages for feature extraction, brain activity recognition and preprocessing. Firstly, the improved Weiner filtering (IWF) approach is used to preprocess the EEG input signal. The relevant features are then extracted using a feature extraction technique from the preprocessed EEG signal. To identify the brain activity, these recovered feature sets are subsequently processed separately using LinkNet and modified bidirectional-long short-term memory (MBi-LSTM). A thorough analysis that takes into account both simulation and experimental calculations is part of the validation process for the LN-MBi-LSTM model. Finally, this study demonstrates the therapeutic potential of the LN-MBi-LSTM framework by presenting a strong and verified model for brain activity recognition. With the highest precision of 0.997, the LinkNet-MBi-LSTM model distinguishes itself from other models and confirms its exceptional capacity to produce accurate positive predictions.

Handling Domain Drift and Unknown Fault Detection in Rotating Machinery Using Few‐Shot Learning With Data Scaling

ABSTRACTThis article presents a novel approach for fault diagnosis in rotating machinery using the few‐shot learning‐based unknown recognition and classification (FSLB‐UR&C) model. The core contribution of this research lies in addressing the challenges of domain drift, unknown fault detection, and uneven sampling intervals. The model effectively incorporates data scaling using Min–Max scaling to manage vibration data drift without altering the source data distribution, significantly extending the classification range. Principal component analysis visualizations substantiate the superior performance of Min–Max scaling over standard methods in processing drifted data, thus enhancing model accuracy. We validated the model on an in‐house bearing simulator and a coal conveyor motor, demonstrating its enhanced ability to classify drifted data and identify previously unknown faults. Additionally, time interpolation was applied to handle irregular sampling intervals, further optimizing the framework's robustness. Compared to other deep learning techniques, the FSLB‐UR&C model with data scaling exhibits markedly improved performance.

Anomaly triplet-net: progress recognition model using deep metric learning considering occlusion for manual assembly work

In this paper, we propose a method for recognizing progress in product assembly considering occlusion using deep metric learning. Visualizing the assembly process in factories is crucial for enhancing work efficiency and minimizing disposal costs. However, there is a problem in that products are managed by pasting them on paper with progress status written on them. We solve the problem of having to manage progress manually. First, the target assembly product is detected from images acquired from a fixed-point camera installed in the factory using a deep learning-based object detection method. Next, the detection area is cropped from the image. Finally, by using a classification method based on deep metric learning on the cropped image, the progress of the product assembly work is estimated as a rough progress step. As a specific progress estimation model, we propose an Anomaly Triplet-Net which is an improved model of the existing method Triplet Loss. This model considers occlusion by learning anomaly samples. In experiments, an 82.9 [%] success rate is achieved for the progress estimation method using Anomaly Triplet-Net. We also experimented with the practicality of the sequence of detection, cropping, and progression estimation, and confirmed the effectiveness of the overall system.

An Emotion Recognition Method for Humanoid Robot Body Movements Based on a PSO-BP-RMSProp Neural Network.

This paper mainly explores the computational model that connects a robot's emotional body movements with human emotion to propose an emotion recognition method for humanoid robot body movements. There is sparse research directly carried out from this perspective to recognize robot bodily expression. A robot's body movements are designed by imitating human emotional body movements. Subjective questionnaires and statistical methods are used to analyze the characteristics of a user's perceptions and select appropriate designs. An emotional body movement recognition model using a BP neural network (EBMR-BP model) is proposed, in which the selected robot's body movements and corresponding emotions are used as inputs and outputs. The corresponding topological architecture, encoding rules, and training process are illustrated in detail. Then, the PSO method and the RMSProp algorithm are introduced to optimize the EBMR-BP method, and the PSO-BP-RMSProp model is developed. Through experiments and comparisons for emotion recognition of a robot's body movements, the feasibility and effectiveness of the EBMR-BP model, with a recognition rate of 66.67%, and the PSO-BP-RMSProp model, with a recognition rate of 88.89%, are verified. This indicates that the proposed method can be used for emotion recognition of a robot's body movements, and optimization can improve emotion recognition. The contributions are beneficial for emotional interaction design in HRI.

CEFM: CLIP Encoded Fusion Model for multimodal humor recognition on memes

CEFM: CLIP Encoded Fusion Model for multimodal humor recognition on memes

Pseudo-Labeling and Time-Series Data Analysis Model for Device Status Diagnostics in Smart Agriculture

This study proposes an automated data-labeling model that combines a pseudo-labeling algorithm with waveform segmentation based on Long Short-Term Memory (LSTM) to effectively label time-series data in smart agriculture. This model aims to address the inefficiency of manual labeling for large-scale data generated by agricultural systems, enhancing the performance and scalability of predictive models. Our proposed method leverages key features of time-series data to automatically generate labels for new data, thereby improving model accuracy and streamlining data processing. By automating the labeling process, we reduce dependence on manual labeling, which is often labor-intensive and prone to errors in large datasets. This approach enables the efficient preparation of labeled data for applications such as anomaly detection, pattern recognition, and predictive modeling in smart agriculture. Experimental results demonstrate that the automated labeling model achieves 89% accuracy in agricultural environments and reduces data processing time by 30%. Future research will focus on extending the model’s applicability to diverse agricultural settings, enhancing generalization performance, and improving real-time processing capabilities, thereby advancing intelligent and sustainable smart agriculture systems.

The Convergence of Artificial Intelligence and Human Marketing: A Framework for Enhanced Customer Insights and Personalization

This article examines the transformative integration of artificial intelligence and human expertise in modern marketing analytics, focusing on customer insight generation and personalization strategies. We present a comprehensive framework for human-AI collaboration in marketing operations through a mixed-methods approach combining quantitative analysis of customer data from 127 retail organizations and qualitative interviews with 34 marketing professionals. The findings reveal that organizations implementing AI-enhanced customer analytics in conjunction with human-driven creative strategy achieved a 47% improvement in customer engagement metrics and a 31% increase in conversion rates compared to traditional approaches. The article demonstrates that while AI excels at real-time pattern recognition and predictive modeling of customer behavior, human marketers provide crucial emotional intelligence and contextual interpretation that significantly enhance the effectiveness of personalization efforts. The article introduces the Dual Intelligence Marketing Framework (DIMF), which outlines optimal integration points between AI capabilities and human expertise throughout the customer journey. The framework addresses critical challenges in implementation, including technical infrastructure requirements, talent adaptation, and ethical considerations. This article contributes to both theoretical understanding and practical application of AI in marketing, offering actionable insights for organizations seeking to leverage the complementary strengths of artificial and human intelligence in their marketing operations.

Accurate Prediction of 327 Rice Variety Growth Period Based on Unmanned Aerial Vehicle Multispectral Remote Sensing

Most rice growth stage predictions are currently based on a few rice varieties for prediction method studies, primarily using linear regression, machine learning, and other methods to build growth stage prediction models that tend to have poor generalization ability, low accuracy, and face various challenges. In this study, multispectral images of rice at various growth stages were captured using an unmanned aerial vehicle, and single-plant rice silhouettes were identified for 327 rice varieties by establishing a deep-learning algorithm. A growth stage prediction method was established for the 327 rice varieties based on the normalized vegetation index combined with cubic polynomial regression equations to simulate their growth changes, and it was first proposed that the growth stages of different rice varieties were inferred by analyzing the normalized difference vegetation index growth rate. Overall, the single-plant rice contour recognition model showed good contour recognition ability for different rice varieties, with most of the prediction accuracies in the range of 0.75–0.93. The accuracy of the rice growth stage prediction model in recognizing different rice varieties also showed some variation, with the root mean square error between 0.506 and 3.373 days, the relative root mean square error between 2.555% and 14.660%, the Bias between1.126 and 2.358 days, and the relative Bias between 0.787% and 9.397%; therefore, the growth stage prediction model of rice varieties can be used to effectively improve the prediction accuracy of the growth stage periods of rice.

Deep transfer learning for microseismic waveforms recognition across geological conditions in TBM tunnels

In deeply buried tunneling projects, geological conditions are often complex and varied. Microseismic monitoring systems are extensively deployed to enhance construction safety. However, when the current geological conditions differ from those present during the signal collection for model training, recognition accuracy tends to decline significantly. Therefore, improving the applicability and stability of microseismic waveform recognition models across varying geological conditions has emerged as a critical challenge. To address this issue, we first analyze the impact of lithological changes and the development of structural planes on the features of microseismic waveforms. Subsequently, we propose a category-domain-aligned transfer learning method that enables the transfer of recognition capabilities across geological conditions by facilitating similar feature extraction and the recognition of cross-geological fracture waveforms. In this model, feature separation modeling enhances the extraction of category features of waveforms under different geological conditions. A deep transfer learning mechanism distinguishes between unique and common features, allowing for the capture of essential features necessary for model parameter updates. Through comparative experiments and feature distribution alignment and visualization, we demonstrate that the accuracy of microseismic waveform recognition across geological conditions achieves 90 %. Additionally, the performance of our method is validated using microseismic signals collected from different sections of the construction site.

A Comprehensive Quality Evaluation for Gentiana Rigescens Franch. by Fingerprinting Combined with Chemometrics and Network Pharmacology.

Gentiana rigescens Franch. (G. rigescens) is a unique traditional medicinal herb from southwestern China, and its clinical mechanism for the treatment of hepatitis and the quality differences between different origins are not clear. The research aims to analyze the mechanisms for the treatment of hepatitis and differences in inter-origin differences using analytical techniques, chemometrics, and network pharmacology. Through infrared spectroscopy, spectral images, and high-performance liquid chromatography (HPLC) analysis, it was found that there were differences in absorbance intensity and significant differences in compound content among the samples' origin. G. rigescens iridoids and flavonoids exert therapeutic effects on hepatitis through multiple targets (GAPDH, EGFR, and MMP9, etc.) and multiple pathways (non-small cell lung cancer, hepatitis C, etc.). The above HPLC, chemometrics, and network pharmacology results revealed that gentiopicroside, and swertiamarine was the best quality marker among origins. The accuracy of the ResNet model train, test, and external validation sets for synchronous spectral images were 100 %, which could be utilized as an effective tool for tracing G. rigescens's origins. The R2 of the calibration and validation sets of the PLSR model was higher than 0.70. This model had excellent predictive performance in determining the content of gentiopicroside and swertiamarine, and could quickly, accurately, and effectively predict these two compounds. The research investigates the differences in G. rigescens origins from multiple perspectives, establishes image recognition models and prediction models, and provides new methods and theoretical basis for quality control of G. rigescens.

Research on oil and gas pipeline leak detection method based on 1DCNN-DBO-LSTM

Abstract Detecting leaks in oil and gas pipelines is crucial for the safe operation of these systems. Current techniques for identifying oil and gas pipeline breaches are insufficient and fail to utilize the temporal attributes of the leak signal. This research proposes a fusion recognition model that integrates a long short-term memory network (LSTM) optimized using a one-dimensional convolutional neural network (1DCNN) with the dung beetle optimization algorithm (DBO). The model initially tackles the issue of excessive depth in the 1DCNN network, which paradoxically results in decreased accuracy and increased computational load. It develops a lightweight 1DCNN network via structural experiments that adaptively extracts data features. Subsequently, to mitigate the effects of the LSTM model's high stochasticity and the challenges associated with manual hyperparameter selection on detection accuracy, an enhanced LSTM model is proposed. This model is optimized through the integration of the Dung Beetle Optimization Algorithm (DBO) to refine the hyperparameters in LSTM. A 1DCNN-DBO-LSTM recognition model is developed, whereby the data features retrieved adaptively from the 1DCNN are fed into the enhanced DBO-LSTM for classification, and the T-SNE dimensionality reduction technique is utilized to visualize the network at each output layer. The model is assessed utilizing the precision and duration measures. The suggested model enhances recognition accuracy and reduces detection time compared to existing advanced models. The approach presented in this work can extract pipeline data features more swiftly and accurately, thus enhancing classification precision.

Research on Target Hybrid Recognition and Localization Methods Based on an Industrial Camera and a Depth Camera in Complex Scenes

In order to improve the target visual recognition and localization accuracy of robotic arms in complex scenes with similar targets, hybrid recognition and localization methods based on an industrial camera and depth camera are proposed. First, according to the speed and accuracy requirements of target recognition and localization, YOLOv5s is introduced as the basic algorithm model for target hybrid recognition and localization. Then, in order to improve the accuracy of target recognition and coarse localization based on an industrial camera (eye-to-hand), the AFPN feature fusion module, simple and parameter-free attention module (SimAM), and soft non-maximum suppression (Soft NMS) are introduced. In order to improve the accuracy of target recognition and fine localization based on a depth camera (eye-in-hand), the SENetV2 backbone network structure, dynamic head module, deformable attention mechanism, and chain-of-thought prompted adaptive enhancer network are introduced. After that, on the basis of constructing a dual camera platform for target hybrid recognition and localization, the hand–eye calibration, collection and production of image datasets required for model training are completed. Finally, for the docking of the oil filling port, the hybrid recognition and localization experimental tests are completed in sequence. The test results show that in target recognition and coarse localization based on the industrial camera, the recognition accuracy of the designed model reaches 99%, and the average localization errors in the horizontal and vertical directions are 2.22 mm and 3.66 mm, respectively. In target recognition and fine localization based on the depth camera, the recognition accuracy of the designed model reaches 98%, and the average errors in depth, horizontal, and vertical directions are 0.12 mm, 0.28 mm, and 0.16 mm, respectively. These not only verify the effectiveness of the target hybrid recognition and localization methods based on dual cameras, but also demonstrate that they meet the high-precision recognition and localization requirements in complex scenes.

Automatic Screening for Children with Speech Disorder Using Automatic Speech Recognition: Opportunities and Challenges

Speech is a fundamental aspect of human life, crucial not only for communication but also for cognitive, social, and academic development. Children with speech disorders (SD) face significant challenges that, if unaddressed, can result in lasting negative impacts. Traditionally, speech and language assessments (SLA) have been conducted by skilled speech-language pathologists (SLPs), but there is a growing need for efficient and scalable SLA methods powered by artificial intelligence. This position paper presents a survey of existing techniques suitable for automating SLA pipelines, with an emphasis on adapting automatic speech recognition (ASR) models for children’s speech, an overview of current SLAs and their automated counterparts to demonstrate the feasibility of AI-enhanced SLA pipelines, and a discussion of practical considerations, including accessibility and privacy concerns, associated with the deployment of AI-powered SLAs.

Advancements in Image Recognition: Comparing CNNs and Vision Transformers

Abstract. This paper explores advancements in image recognition technologies, highlighting the shift from conventional methodologies to contemporary deep learning techniques, specifically focusing on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The study examines key architectures including CNNs, and various Transformer-based models, analyzing their performance evaluating their effectiveness in diverse tasks such as image classification, object detection, and facial recognition. The research highlights the strengths and limitations of CNNs and ViTs, focusing on their ability to handle complex and diverse datasets. A detailed comparative analysis is conducted, emphasizing performance metrics, robustness, and adaptability across different image recognition scenarios. The results reveal that while CNNs excel in traditional image processing tasks, ViTs demonstrate significant improvements in capturing long-range dependencies, thereby enhancing recognition accuracy in more complex contexts. This analysis offers critical perspectives on selecting and applying image recognition models, guiding future exploration and practical use in various industries. It underscores the impact of deep learning innovations on advancing image recognition capabilities and highlights potential directions for ongoing development in the field.

Identification strategy of wild and cultivated Astragali Radix based on REIMS combined with two-dimensional LC-MS

A rapid and real-time method was established based on the combination of rapid evaporative ionization mass spectrometry (REIMS) and two-dimensional liquid chromatography mass spectrometry (2DLC-MS) for identification of wild Astragali Radix (WAR) and cultivated AR (CAR). The samples were analyzed under ambient ionization without time-consuming sample preparation. The phenotypic data of WAR and CAR were used to develop a real-time recognition model. Subsequently, the compounds in these two species were comprehensively characterized based on 2DLC-MS, and 45 different compounds were screened out by multivariate statistical analysis. A semi-quantitative method for 45 different compounds was established based on ultrahigh-performance liquid chromatography/quadrupole-linear ion trap mass spectrometry (UHPLC-QTRAP-MS). The results showed that the relative content of most compounds in WAR was higher than in CAR. In summary, the method has demonstrated remarkable performance in distinguishing between WAR and CAR, providing a reference in the field of traditional Chinese medicine (TCM) analysis and identification.