Efficient Recognition Research Articles

A VOx-based optoelectronic memristor for application in visual perception

Abstract While biological vision systems excel at in-memory processing with low power consumption, traditional silicon-based vision chips struggle with high energy demands. This gap motivates the exploration of alternative materials for artificial intelligence applications. This paper presents a VOx-based optoelectronic synaptic memristive device. The proposed artificial synaptic device ITO/VO x /Pt mimics biological functions such as potentiation (P), depression (D), long-term memory, short-term memory (STM), and paired-pulse facilitation (PPF). The PPF index, standing at 105%, suggests a favorable pattern in STM function. The device served as synapses within a spiking neural network showing an achievable pattern classification accuracy of 88.68%, highlighting the potential of the VO x synaptic device for pattern classification tasks. The suggested VO x -based synaptic devices could represent an efficient pattern recognition and visual perception application.

Alphabet Handwriting Recognition: From Wood-Framed Hydrogel Arrays Design to Machine Learning Decoding.

Handwriting recognition is a highly integrated system, demanding hardware to collect handwriting signals and software to deal with input data. Nonetheless, the design of such a system from scratch with sustainable materials and an easily accessible computing network presents significant challenges. In pursuit of this goal, a flexible, and electrically conductive wood-derived hydrogel array is developed as a handwriting input panel, enabling recognizing alphabet handwriting assisted by machine learning technique. For this, lignin extraction-refill, polypyrrole coating, and polyacrylic acid filling, endowing flexibility, and electrical conduction to wood are sequentially implemented. Subsequently, these woods are manufactured into a 5×5 array, creating a matrix of signals upon handwriting. Efficient handwritten recognition is then achieved through appropriate manual feature extraction and algorithms with low complexity within a computing network, as demonstrated in this work, the strategic choice of expertise-based feature engineering and simplified algorithms effectively boost the overall model performance on handwriting recognition. With potential adaptability, further applications in customized wearable devices and hands-on healthcare appliances are envisioned.

A Hybrid Recognition Framework for Highly Interacting Machining Features Based on Primitive Decomposition, Learning and Reconstruction

For the highly interacting machining features, Layered Projection Decomposition Method presents inferior recognition efficiency and accuracy, due to its high-cost 3D projection and failures in determining projection faces for internal occluded faces. To address these issues, we propose a potential hybrid recognition framework. We first introduce a straightforward adjacent projection wire (APW) over UV wires, automatically restoring the full projection wires from highly interacting features. Building on APWs, an efficient hybrid boundary representation and its corresponding unambiguous primitive definitions are proposed by combing with graph-based boundary representations. Subsequently, we design an efficient primitive decomposition method by introducing primitive boundary matching to decide the initial projection faces, and introducing iterative projection boundary expansion to complete the full primitives from occluded faces. Moreover, we establish an efficient Graph Neural Network to learn the distinguishable distributions over the decomposed primitives. Specifically, an Adjacency Attention Unit is proposed to automatically perceive the influence weight of adjacent nodes, leading to more discriminative self-adaptive shape embedding for efficient primitive recognition. Finally, we summarize convenient reconstruction rules to correct the wrong predictions of feature faces with indistinguishable adjacent relationships. To evaluate the effectiveness of the proposed recognition framework, CAD models of complex aircraft structural parts are collected to present a challenging machining feature dataset. Extensive numerical experiments demonstrate that the proposed hybrid recognition framework enables significant improvements over the state-of-the-art machining feature recognition techniques.

A flexible ten carbon long-chain salamo-like fluorescent probe for highly efficient and selective recognition of Cr2O72− ions, mechanism and practical application

A flexible ten carbon long-chain salamo-like fluorescent probe for highly efficient and selective recognition of Cr2O72− ions, mechanism and practical application

A lightweight and explainable model for driver abnormal behavior recognition

With the advancement of intelligent transportation systems, accurate identification of driver abnormal behavior is crucial for enhancing road safety. However, the limited computing power of vehicular systems poses a challenge for running efficient and explainable behavior recognition models. This paper proposes a lightweight and explainable driver abnormal behavior recognition model based on an improved You Only Look Once version 8 (YOLOv8). Firstly, a Spatial and Channel Reconstruction Convolution (SCConv) module is introduced to optimize the Convolution to Feature (C2f) structure, enhancing the model's feature extraction capabilities while reducing parameter redundancy. Secondly, a Spatial Pyramid Pooling with Fast Large Separable Kernel Attention (SPPF-LSKA) module is designed to better capture image context and integrate global information. Additionally, a Dynamic upsample (Dysample) module is introduced to improve the model's ability to capture subtle driver movements. Lastly, a Lightweight Shared Group Normalization Convolution Detection Head (LSGCDH) is designed to enhance the model's generalization ability, significantly reducing the model's computational load, parameter count, and size. Experimental results demonstrate that our approach has significant advantages for edge device deployment compared to mainstream algorithms. The visualization results effectively corroborate the role of each improved structure, enhancing the explainability of the abnormal behavior recognition model, which is beneficial for deployment in vehicular systems and contributes to improving road traffic safety.

Beta-Cyclodextrin-Modified Covalent Organic Framework Nanochannel for Electrochemical Chiral Recognition of Amino Acids.

The chiral recognition and separation of enantiomers are of great importance for biological research and the pharmaceutical industry. Preparing homochiral materials with adjustable size and chiral binding sites is beneficial for achieving an efficient chiral recognition performance. Here, a homochiral covalent organic framework membrane modified with β-cyclodextrin (CD-COF) was constructed, which was subsequently utilized as an electrochemical sensor for the enantioselective sensing of tryptophan (Trp) molecules. The preferential adsorption of l-Trp over d-Trp at the β-CD sites can enhance the surface charge density and hydrophilicity of the CD-COF membrane, resulting in an increased transmembrane ionic current. Trp enantiomers with concentrations down to 0.28 nM can be effectively discriminated. The l-/d-Trp recognition selectivity increases with the Trp concentration and reaches a value of 19.2 at 1 mM. The selective adsorption of l-Trp to the CD-COF membrane will also hinder its transport, resulting in a l-/d-Trp permeation selectivity of 15.3. This study offers a new strategy to construct homochiral porous membranes and achieve efficient chiral sensing and separation.

Splicing Dysregulation of Non-Canonical GC-5′ Splice Sites of Breast Cancer Susceptibility Genes ATM and PALB2

Background/Objectives: The non-canonical GC-5′ splice sites (5′ss) are the most common exception (~1%) to the classical GT/AG splicing rule. They constitute weak 5′ss and can be regulated by splicing factors, so they are especially sensitive to genetic variations inducing the misrecognition of their respective exons. We aimed to investigate the GC-5′ss of the breast/ovarian cancer susceptibility genes, ATM (exon 50), BRIP1 (exon 1), and PALB2 (exon 12), and their dysregulation induced by DNA variants. Methods: Splicing assays of the minigenes, mgATM_49-52, mgBRIP1_1-2, and mgPALB2_5-12, were conducted to study the regulation of the indicated GC-5′ss. Results: A functional map of the splicing regulatory elements (SRE) formed by overlapping exonic microdeletions revealed three essential intervals, ATM c.7335_7344del, PALB2 c.3229_3258del, and c.3293_3322del, which are likely targets for spliceogenic SRE-variants. We then selected 14 ATM and 9 PALB2 variants (Hexplorer score < −40) located at these intervals that were assayed in MCF-7 cells. Nine ATM and three PALB2 variants affected splicing, impairing the recognition of exons 50 and 12, respectively. Therefore, these variants likely disrupt the active SREs involved in the inclusion of both exons in the mature mRNA. DeepCLIP predictions suggested the participation of several splicing factors in exon recognition, including SRSF1, SRSF2, and SRSF7, involved in the recognition of other GC sites. The ATM spliceogenic variants c.7336G>T (p.(Glu2446Ter)) and c.7340T>A (p.(Leu2447Ter)) produced significant amounts of full-length transcripts (55–59%), which include premature termination stop codons, so they would inactivate ATM through both splicing disruption and protein truncation mechanisms. Conclusions: ATM exon 50 and PALB2 exon 12 require specific sequences for efficient recognition by the splicing machinery. The mapping of SRE-rich intervals in minigenes is a valuable approach for the identification of spliceogenic variants that outperforms any prediction software. Indeed, 12 spliceogenic SRE-variants were identified in the critical intervals.

Predictive immunoinformatics reveal promising safety and anti-onchocerciasis protective immune response profiles to vaccine candidates (Ov-RAL-2 and Ov-103) in anticipation of phase I clinical trials.

Onchocerciasis (river blindness) is a debilitating tropical disease that causes significant eye and skin damage, afflicting millions worldwide. As global efforts shift from disease management to elimination, vaccines have become crucial supplementary tools. The Onchocerciasis Vaccine for Africa (TOVA) Initiative was established in 2015, to advance at least one vaccine candidate initially targeting onchocerciasis in infants and children below 5 years of age, through Phase I human trials by 2025. Notably, Ov-RAL-2 and Ov-103 antigens have shown great promise during pre-clinical development, however, the overall success rate of vaccine candidates during clinical development remains relatively low due to certain adverse effects and immunogenic limitations. This study, thus, aimed at predicting the safety and immunogenicity of Ov-RAL-2 and Ov-103 potential onchocerciasis vaccine candidates prior to clinical trials. Advanced molecular simulation models and analytical immunoinformatics algorithms were applied to predict potential adverse side effects and efficacy of these antigens in humans. The analyses revealed that both Ov-RAL-2 and Ov-103 demonstrate favourable safety profiles as toxicogenic and allergenic epitopes were found to be absent within each antigen. Also, both antigens were predicted to harbour substantial numbers of a wide range of distinct epitopes (antibodies, cytokines, and T- Cell epitopes) associated with protective immunity against onchocerciasis. In agreement, virtual vaccination simulation forecasted heightened, but sustained levels of primary and secondary protective immune responses to both vaccine candidates over time. Ov-103 was predicted to be non-camouflageable, as it lacked epitopes identical to protein sequences in the human proteome. Indeed, both antigens were able to bind with high affinity and activate the innate immune TLR4 receptor, implying efficient immune recognition. These findings suggest that Ov-RAL-2 and Ov-103 can induce sufficient protective responses through diverse humoral and cellular mechanisms. Overall, our study provides additional layer of evidence for advancing the clinical development of both vaccine candidates against onchocerciasis.

Perturbation defense ultra high-speed weak target recognition

Ultra high-speed target recognition in complex electromagnetic environments is a critical and fundamental machine perception issue. It is difficult to ensure privacy protection and intelligent confrontation with centralized training in many practical situations. In this paper, an efficient ultra high-speed target recognition approach, named InVision, for robot systems is proposed using deep trustworthy federated learning (DTFL). InVision is accurate, safe, fast, and robust. Particularly, geometric component transformer (GCT) is presented to significantly promote neural element's complex representation description ability. And an ambiguity-aware cooperative learning (AACL) scheme is developed to relieve the noisy label problem. Moreover, decentralized federated training (DFT) is designed to mitigate the intractable privacy protection problem, to efficiently search for similarities and reduce the representation redundancy. Furthermore, to promote the running speed of the system in real-world environments, a lightweight deep architecture, called Mobile-XB, is developed. Extensive quantitative and qualitative experiments are carried out, and the results demonstrate that InVision greatly outperforms the outstanding comparison methods, establishing efficient connections and extraction, and providing security guarantees.

Encoding human activities using multimodal wearable sensory data

Human Activity Recognition (HAR) is the task to automatically analyze and recognize human body gestures or actions. HAR using time-series multi-modal sensory data is a challenging and important task in the field of machine learning and feature engineering due to its increasing demands in numerous real-world applications such as healthcare, sports and surveillance. Numerous daily wearable devices e.g., smartphones, smartwatches, and smart glasses can be used to collect and analyze the human activities on an unprecedented scale. This paper presents a generic framework to recognize the different human activities using continuous time-series multimodal sensory data of these smart gadgets. The proposed framework follows the channel of Bag-of-Features which consists of four steps: (i) Data acquisition and pre-processing, (ii) codebook computation, (iii) feature encoding, and (iv) classification. Each step in the framework plays a significant role to generate an appropriate feature representation of raw sensory data for efficient activity recognition. In the first step, we employed a simple overlapped-window sampling approach to segment the continuous time-series sensory data to make it suitable for activity recognition. Secondly, we build a codebook using k-means clustering algorithm to group the similar sub-sequences. The center of each group is known as codeword and we assume that it represents a specific movement in the activity sequence. The third step consists of feature encoding which transform the raw sensory data of activity sequence into its respective high-level representation for the classification. Specifically, we presented three reconstruction-based encoding techniques to encode sensory data, namely: Sparse Coding, Local Coordinate Coding, and Locality-constrained Linear Coding. The segmented activity sub-sequences are transformed to high-level representation using these techniques and earlier computed codebook. Finally, the encoded features are classified using a simple Random Forest classifier. The proposed HAR framework using three different encoding techniques is evaluated on three large benchmark datasets: UniMiB-SHAR dataset, MHEALTH dataset and WISDM dataset and their results are compared with most recent state-of-the-art techniques. It outperforms the existing techniques and achieves 98.39%, 99.5%, and 99.4% recognition scores on UniMiB-SHAR dataset, MHEALTH dataset, and WISDM dataset respectively. The excellent recognition results and computational analysis confirms the effectiveness and efficiency of the proposed framework.

A comprehensive review of approaches for spatial domain recognition of spatial transcriptomes.

In current bioinformatics research, spatial transcriptomics (ST) as a rapidly evolving technology is gradually receiving widespread attention from researchers. Spatial domains are regions where gene expression and histology are consistent in space, and detecting spatial domains can better understand the organization and functional distribution of tissues. Spatial domain recognition is a fundamental step in the process of ST data interpretation, which is also a major challenge in ST analysis. Therefore, developing more accurate, efficient, and general spatial domain recognition methods has become an important and urgent research direction. This article aims to review the current status and progress of spatial domain recognition research, explore the advantages and limitations of existing methods, and provide suggestions and directions for future tool development.

Intelligent guide RNA: dual toehold switches for modulating luciferase in the presence of trigger RNA

The CRISPR system finds extensive application in molecular biology, but its continuous activity can yield adverse effects. Leveraging programmable CRISPR/Cas9 function via nano-device mediation effectively mitigates these drawbacks. The integration of RNA-sensing platforms into CRISPR thus empowers it as a potent tool for processing internal cell data and modulating gene activity. Here, an intelligent guide RNA—a cis-repressed gRNA synthetic circuit enabling efficient recognition of specific trigger RNAs—is developed. This platform carries two toehold switches and includes an inhibited CrRNA sequence. In this system, the presence of cognate trigger RNA promotes precise binding to the first toehold site, initiating a cascade that releases CrRNA to target a reporter gene (luciferase) in this study. Decoupling the CrRNA segment from the trigger RNA enhances the potential of this genetic logic circuit to respond to specific cellular circumstances, offering promise as a synthetic biology platform.

Efficient object recognition under cluttered scenes via descriptor-based matching and single point voting

This paper addresses the problem of recognizing multiple objects and multiple instances from point clouds. Whereas existing methods utilize descriptors on 3D fields or pointwise voting to achieve this task, our framework takes advantage of both descriptor-based and voting-based schemes to realize more robust and efficient prediction. Specifically, we propose a novel and robust descriptor called an orientation-enhanced fast point feature histogram (OE-FPFH) to describe points in both the object model and scene, and further to build the correspondence set. The OE-FPFH integrates an orientation vector through mining the geometric tensor of the local structure of a surface point, which is more representative than the original FPFH descriptor. To improve voting efficiency, we devise a novel single-point voting mechanism (SPVM), which constructs a unique local reference frame (LRF) on a single point using the orientation vector. The SPVM takes as input the corresponding point set and can generate a pose candidate for each correspondence. The process is realized by matching LRFs from two corresponding points. All pose candidates are subsequently divided into clusters and aggregated using the K-means clustering algorithm to deduce the poses for different objects or instances in the scene. Experiments on three challenging datasets demonstrate that our method is effective, efficient, and robust to occlusions and multiple instances.

General and Modular Synthesis of Covalent Organic Cages for Efficient Molecular Recognition.

Cage-type structures based on coordination and dynamic covalent chemistry have the characteristics of facile and efficient preparation but poor stability. Chemically stable organic cages, generally involving fragment coupling and multi-step reactions, are relatively difficult to synthesize. Herein, we offer a general and modular strategy to customize covalent organic cages with diverse skeletons and sizes. First, one skeleton (S) module with three extension (E) modules and three reaction (R) modules are connected by one- or two-step coupling to get the triangular monomer bearing three reaction sites. Then one-pot Friedel-Crafts condensation of the monomer and linking module of paraformaldehyde produces the designed organic cages. The cage forming could be regulated by the geometrical configuration of monomeric blocks. The S-E-R angles in the monomer is crucial; only 120° (2,4-dimethoxyphen as reaction module) or 60° (2,5-dimethoxyphen as reaction module) angle between S-E-R successfully affords the resulting cages. By the rational design of the three modules, a series of organic cages have been constructed. In addition, the host-guest properties show that the representative cages could strongly encapsulate neutral aromatic diimide guests driven by solvophobic interactions in polar solvents, giving the highest association constant of (2.58±0.18)×105 M-1.

RAPNet: Resolution-Adaptive and Predictive Early Exit Network for Efficient Image Recognition

RAPNet: Resolution-Adaptive and Predictive Early Exit Network for Efficient Image Recognition

Chiral Metal-Organic Framework Films with Ordered Macropores for Enantioselective Analysis of Proteins.

Chiral film-based sensors show great promise for discriminating between enantiomers due to their miniaturization and low power consumption. However, their practical use is hindered by the trade-off between enantioselectivity and mass transfer capability, especially concerning biomacromolecules such as proteins. In this work, we present an effective and straightforward method for creating highly organized macropores within crystalline chiral metal-organic framework (CMOF) films. This approach harnesses the shaping influence of a polystyrene nanosphere template and the crystallization induced by the liquid dielectric barrier discharge plasma. The resultant highly ordered macro-microporous structures improve mass diffusion and access to chiral active sites in the hierarchical CMOF films. Coupled with their inherent chirality, strong fluorescence emission, high crystallinity, and exceptional stability, these attributes endow these CMOF films with enhanced sensing capabilities for chiral molecules. Particularly, the macro-microporous structure facilitates efficient protein recognition, overcoming a significant challenge encountered by MOFs due to protein dimensions surpassing MOF pore sizes. These films exhibit increased enantioselectivity, better limits of detection, and wider linear ranges compared with purely microporous CMOF films. This study thus provides a powerful synthetic approach for hierarchical CMOF films, addressing the limitations of traditional thin film sensors and opening an avenue for efficient chiral sensing of large biomacromolecules.

General and Modular Synthesis of Covalent Organic Cages for Efficient Molecular Recognition

AbstractCage‐type structures based on coordination and dynamic covalent chemistry have the characteristics of facile and efficient preparation but poor stability. Chemically stable organic cages, generally involving fragment coupling and multi‐step reactions, are relatively difficult to synthesize. Herein, we offer a general and modular strategy to customize covalent organic cages with diverse skeletons and sizes. First, one skeleton (S) module with three extension (E) modules and three reaction (R) modules are connected by one‐ or two‐step coupling to get the triangular monomer bearing three reaction sites. Then one‐pot Friedel‐Crafts condensation of the monomer and linking module of paraformaldehyde produces the designed organic cages. The cage forming could be regulated by the geometrical configuration of monomeric blocks. The S−E−R angles in the monomer is crucial; only 120° (2,4‐dimethoxyphen as reaction module) or 60° (2,5‐dimethoxyphen as reaction module) angle between S−E−R successfully affords the resulting cages. By the rational design of the three modules, a series of organic cages have been constructed. In addition, the host‐guest properties show that the representative cages could strongly encapsulate neutral aromatic diimide guests driven by solvophobic interactions in polar solvents, giving the highest association constant of (2.58±0.18)×105 M−1.

Multi-branch deep learning neural network prediction model for the development of angular biosensors based on sEMG.

Human gait motion intention recognition is very important for the lower extremity exoskeleton robot to accurately synchronize and respond to the user's natural motion. And motion intention recognition is generally performed through sEMG. Deep learning neural networks perform well in dealing with high-dimensional data and nonlinear relationships such as sEMG, but different deep learning neural networks have their own advantages in dealing with different types of data. Therefore, a multi-branch deep learning neural network, which enables different neural networks to process different feature items, could achieve more accurate and efficient motion intention recognition. The purpose of this study is to 1) Establish a multi-branch deep learning neural network model to achieve accurate gait recognition and effective estimation of joint angles. 2) Quantify the performance of the multi-branch deep learning neural network model in gait recognition and joint angle prediction using sEMG. This study involved the collection of sEMG and plantar pressure data during walking in human subjects. Firstly, the collected signals are filtered and denoised to ensure the quality and reliability of the data. Calculate the time domain features and the frequency domain features to capture the key information of gait. Then, using the sensitivity difference of different structural neural networks to different feature data, a multi-branch deep learning neural network model is developed, in which the extracted features are used as the input of the model. The output of the model includes gait cycle and joint angle, so as to realize the accurate recognition of human gait and the effective estimation of joint angle. The results show that the proposed method has high accuracy in identifying human gait and estimating joint angles. The multi-branch neural network model successfully integrates time-domain and frequency-domain features and provides reliable prediction of gait cycle and joint angle. The highest accuracy of gait recognition is 95.42%, the lowest is 90.11%, and the average is 92.16%. The average error of joint angle estimation is 3.19. This study designed a human walking gait recognition and joint angle prediction model to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.

A novel ultra-long carbon-chain salamo-like fluorescent chemosensor with good flexibility: Synthesis, crystal structure, Pb2+ ion recognition and mechanism exploration

A novel ultra-long carbon-chain salamo-like fluorescent chemical probe DMS containing ten methylene groups (DMS, 6,6′-dimethoxy-2,2′-[1,10-(decanedioxy)bis(nitromethyldyne)]diphenol), was synthesized based on the 3‑methoxy salicylaldehyde unit, and its single crystals were obtained. The single crystal structure for the probe DMS molecule was determined. Research has shown that the fluorescent probe DMS can achieve efficient and selective recognition of Pb2+ ions, with a binding constant Ka = 1.42 × 104 M-1. The detection limit is as low as LOD = 1.31 × 10–7 M, and quantification limit is as low as LOQ = 4.36 × 10–7 M The possible identification mechanism of the fluorescent chemosensor DMS to Pb2+ions was analyzed and studied through fluorescence titration test, nuclear magnetic changes and Job′s plot exprements, DFT calculation et al. The results indicated that the fluorescent chemosensor DMS forms a coordination compound with Pb2+through 1:1 coordination, enhancing its fluorescence and resulting in the coordinated fluorescence enhancement effect.

Wafer-scale integration of two-dimensional perovskite oxides towards motion recognition

Two-dimensional semiconductors have shown great potential for the development of advanced intelligent optoelectronic systems. Among them, two-dimensional perovskite oxides with compelling optoelectronic performance have been thriving in high-performance photodetection. However, harsh synthesis and defect chemistry severely limit their overall performance and further large-scale heterogeneous integration. Here, we report the wafer-scale integration of highly oriented nanosheets by introducing a charge-assisted oriented assembly film-formation process and confirm its universality and scalability. The shallow-trap dominance induced by structural optimization endows the device with a distinguished performance balance, including high photosensitivity close to that of single nanosheet units and fast response speed. An integrated ultra-flexible 256-pixel device demonstrates the versatility of material-to-substrate integration and conformal imaging functionality. Moreover, the device achieves efficient recognition of multidirectional motion trajectories with an accuracy of over 99.8%. Our work provides prescient insights into the large-area fabrication and utilization of 2D perovskite oxides in advanced optoelectronics.