Recognition Ability Research Articles

Preparation and Performance Research of Pb(II)-Imprinted Acrylonitrile-Co-Acrylic Acid Composite Material with Modified Sand Particles as Carrier

Lead (Pb) is classified as a prevalent metallic pollutant, significantly impacting the ecological environment, especially human health. Consequently, it is crucial to develop adsorbent materials that are environmentally friendly, cost-effective, and which possess high selectivity. This study aims to fabricate a Pb(II)-imprinted acrylonitrile-co-acrylic acid composite material by using modified sand particles as the carrier, and then to investigate its properties. Through pretreatment of sand particles, acrylonitrile and acrylic acid were polymerized on the surface of modified sand particles, and Pb(II) served as a template ion for imprinting. A variety of characterization methods were used to verify the composite material and conduct an analysis of its morphology, chemical composition, and pore characteristics. The adsorption efficiency of this composite material for Pb(II) is comprehensively explored, with the process involving adsorption kinetics, adsorption isotherms, selective adsorption, and reuse experiments. Through static adsorption experiments, multiple elements influencing the adsorption ability of the composite material towards Pb(II) are investigated. It was demonstrated by the results that the composite material prepared possesses a rich pore structure and excellent Pb(II) recognition ability. The investigation on adsorption kinetics is in line with the quasi-first-order and quasi-second-order kinetic models, while the adsorption isotherm, obeys the Langmuir model. The ideal adsorption conditions were pH = 7, with the adsorption reaching equilibrium within 105 min. Even when multiple interfering ions were present, it still had high selectivity for Pb(II). The composite material showed an adsorption saturation capability reaching 41.83 mg·g−1, considerably surpassing the non-imprinted counterpart. After being reused eight times, the composite material can still maintain an adsorption efficiency for Pb(II) that is above 79% and demonstrates high potential in the practical application environment.

A facial expression recognition network using hybrid feature extraction.

Facial expression recognition faces great challenges due to factors such as face similarity, image quality, and age variation. Although various existing end-to-end Convolutional Neural Network (CNN) architectures have achieved good classification results in facial expression recognition tasks, these network architectures share a common drawback that the convolutional kernel can only compute the correlation between elements of a localized region when extracting expression features from an image. This leads to difficulties for the network to explore the relationship between all the elements that make up a complete expression. In response to this issue, this article proposes a facial expression recognition network called HFE-Net. In order to capture the subtle changes of expression features and the whole facial expression information at the same time, HFE-Net proposed a Hybrid Feature Extraction Block. Specifically, Hybrid Feature Extraction Block consists of parallel Feature Fusion Device and Multi-head Self-attention. Among them, Feature Fusion Device not only extracts the local information in expression features, but also measures the correlation between distant elements in expression features, which helps the network to focus more on the target region while realizing the information interaction between distant features. And Multi-head Self-attention can calculate the correlation between the overall elements in the feature map, which helps the network to extract the overall information of the expression features. We conducted a lot of experiments on four publicly available facial expression datasets and verified that the Hybrid Feature Extraction Block constructed in this paper can improve the network's recognition ability for facial expressions.

Research on peanut pedigree analysis and variety identification methods based on deep features extraction and hierarchical clustering

Abstract In order to screen high-quality peanut pod varieties on food processing production lines and promote the sustainable development of the peanut as well as the expansion of its consumer market, this study improved the recognition ability of peanut pod varieties and the efficiency of deep feature extraction by optimizing the ResNet50 deep learning network model. Experimental results showed that the accuracy of the optimized network model reached 91.6%, which was 2.1% higher than the original ResNet50 model. Additionally, this study extracted the deep features of the appearance morphology of peanut pods, used the agglomerative clustering method to explore the genetic relationship of hybrid offspring varieties under the same line, and constructed a pedigree diagram containing 18 varieties. These research findings provide a crucial scientific foundation for the cultivation of high-quality peanut varieties. The selected high-quality peanuts not only enhance the added value of the peanut industry but also further expand the market potential of peanut by-products.

A Target Domain-Specific Classifier Weight Partial Transfer Adversarial Network for Bearing Fault Diagnosis

In actual industry applications, the failure categories of practical equipment are usually a subset of laboratory conditions failure categories. Due to the strict constraints, partial transfer learning can address a more practical diagnostic scenario. In view of this, this paper proposes a target domain-specific classifier weight partial transfer adversarial network. Initially, the 1-D convolutional neural network is employed as the basic architecture. By training the domain discriminator and feature generator with an adversarial strategy, the recognition ability of the domain discriminant network and the feature extraction ability of the feature generation network can be enhanced. After that, a weighted learning strategy is introduced to guide the model to learn the cross-domain invariant feature. Also, a specific target domain classifier is utilized to redivide the target domain decision boundary to accurately classify the unlabeled target domain samples. Finally, five mainstream deep neural network methods are taken for comparison using the data from Western Reserve University and the motor-magnetic brake test designed by us. The results show that the proposed method reaches 90.18% and 96.53% classification accuracy on two datasets, respectively, which demonstrates superior performance compared with the state-of-the-art methods.

Long-Term Auditory and Speech Outcomes of Cochlear Implantation in Children with IP-I Malformation.

This study aimed to investigate the long-term auditory and speech outcomes in children with Incomplete Partition Type I (IP-I) who underwent cochlear implantation (CI) and compared their progress to implanted children with normal cochlea. This study tracked 17 children with IP-Ι for an average of 3.5 years post-implantation. A control group with normal cochlea was also tracked. Regular assessments, including aided hearing threshold, categories of auditory performance (CAP), and speech intelligibility rating (SIR), were conducted every 6 months for the first 2 years post-CI and annually thereafter. Speech recognition was tested for children who could cooperate with it. The aided hearing threshold of IP-I children had improved significantly from 90.51 dB HL before CI to 47.02 dB HL in the sixth-month post-CI, and it had further improved to 26.27 dB HL after more than 48 months post-CI. Meanwhile, their median CAP scores had improved from 0 to 6.5 and median SIR scores from 1 to 4 over the same period. There was no significant difference in the improvement of mean aided hearing thresholds over time between the IP-I and control groups postoperation. However, IP-I children showed slower progress in CAP and SIR scores and had lower recognition rates for monosyllabic and disyllabic words compared with the control group. Children with IP-Ι showed continuous but slower improvement in auditory and speech capabilities post-CI compared to those with normal cochlea. Their speech recognition ability was also inferior. III Laryngoscope, 2025.

A dynamically assembled bionic ion pump interface towards high-rate and stable-cycling zinc metal batteries

A bionic ion pump interface is developed by introducing acetylated proteins (α-HPace) with strong Zn2+ recognition ability.

Construction of a regulable chiral recognition platform based on the photothermal effect of popcorn-like gold nanoparticles/bovine serum albumin.

Although the chiral recognition ability of nanomaterials is known to play a crucial role in the chiral discrimination of enantiomers, it remains challenging to precisely regulate the chiral recognition ability predictably and on demand. In this work, a regulable chiral recognition platform is designed based on the photothermal effect of popcorn-like gold nanoparticles (AuNPs)/bovine serum albumin (BSA). First, AuNPs with excellent chiral recognition ability are prepared for the discrimination of tyrosine (Tyr) enantiomers. Subsequently, AuNPs can be combined with BSA through the Au-S bond. The obtained AuNPs/BSA exhibits the opposite chiral recognition ability to AuNPs due to the inherent chirality of BSA. Interestingly, BSA can also be destroyed relying on the photothermal effect of AuNPs and the excitation of near-infrared (NIR) light. Therefore, the resulting AuNPs/BSA/NIR reversibly displays the same chiral recognition ability as AuNPs. A regulable chiral recognition platform is constructed for chiral discrimination of Tyr enantiomers, which can satisfy the purpose of predictable and on-demand regulation of the recognition ability of nanomaterials and might be a potential candidate for detection and therapy in vivo.

Fire Video Recognition Based on Local and Global Adaptive Enhancement

Fires pose an enormous risk to human life and property. In the domain of fire warning, earlier approaches leveraging computer vision have achieved significant progress. However, these methods ignore the local and global motion characteristics of flames. To address this issue, a Local and Global Adaptive Enhancement (LGAE) network is proposed, which mainly includes the backbone block, the Local Adaptive Motion Enhancement (LAME) block, and the Global Adaptive Motion Enhancement (GAME) block. Specifically, the LAME block is designed to capture information about local motion, and the GAME block is devised to enhance information about global motion. Through the utilization of these two blocks, the fire recognition ability of LGAE is improved. To facilitate the research and development in the domain of fire recognition, we constructed a Large-scale Fire Video Recognition (LFVR) dataset, which includes 11,560 video clips. Extensive experiments were carried out on the LFVR and FireNet datasets. The F1 scores of LGAE on LFVR and FireNet were 88.93% and 93.18%, respectively. The experimental outcomes indicate that LGAE performs better than other methods on both LFVR and FireNet.

Are domestic chickens born with predator recognition? Validation of a sound playback experiment.

Predation risk can influence behavioral decisions of animals in various ways. Prey animals have the opportunity to choose antipredation behaviors and escape strategies only by quickly and accurately identifying predators. As precocial birds, domestic chickens (Gallus gallus domesticus) have no adaptation period after hatching and must immediately survive under predation risk. They possess a strong ability to identify threats through vocalizations. To explore whether domestic chickens have innate predator recognition ability and whether the antipredation behavior of breeding chickens is stronger than that of non-breeding chickens. We tested the antipredation behaviors of three types of flocks (non-breeding chickens; hen with chicks; isolated chicks) of domestic chickens in response to sparrowhawk (Accipiter nisus) calls using playback experiments, while Oriental turtle dove (Streptopelia orientalis) calls were used as a control. We found that breeding hens are significantly more vigilant than non-breeding chickens. We also found that although isolated chicks can exhibit antipredator behavior, they cannot accurately identify the calls of predators and non-predators. Therefore, it can be concluded that domestic chickens exhibit varying degrees of vigilance towards predator calls at different stages of their life history. Reproductive costs can lead to increased vigilance in domestic chickens. The accurate identification of predators by domestic chickens is not innate, but gradually formed over time.

Fluorescent distinguishing flavonoid glycosides against aglycones based on the selective recognization of boric acid-functional Eu(III)-organic framework.

Flavonoid glycosides are formed by dehydration condensation of aglycones and sugar molecules. Therefore, discrimination of flavonoid glycosides from their corresponding aglycones is a challenging task because they contain the same aglycone part in their molecular structures. Herein, boric acid-functional Eu(III)-organic framework (BA-Eu-MOF) was applied to discriminate flavonoid glycosides including baicalin (Bai), wogonoside (Wog), rutin (Rut), puerarin (Pue), quercitrin (Que) and astragalin (Ast) from their corresponding aglycones for the first time. Besides as organic ligand to sensitize the luminescence of Eu3+ through "antenna" effect, 5-boronobenzene-1,3 dicarboxylic acid provided recognition site for flavonoid glycosides. Infrared, fluorescence, UV-vis, and mass spectra were used to investigate the recognition reaction between BA-Eu-MOF and flavonoid glycosides. The data indicated that the cis-diols of flavonoid glycosides from sugars covalently bonded to boric acid group to form cyclic boronic esters, which quenched the fluorescence of BA-Eu-MOF at 620nm through decreasing the intersystem efficiency, inner filter effect and photoelectron transfer. In contrast, aglycones could not alter the fluorescence of BA-Eu-MOF because of no covalent bond between them. This probe exhibited high sensitivity towards flavonoid glycosides with the low detection limits of 3.3nM, 3.5nM, 33nM, 56nM, 5.1nM and 5.5nM for Bai, Que, Wog, Ast, Pue and Rut, respectively. The unique recognition ability of boric acid group enables selective and sensitive detection of flavonoid glycosides without the interference of their corresponding aglycones.

Optimized separation of astaxanthin stereoisomers from microbial sources using chiral HPLC.

Astaxanthin (AST) is a high-value antioxidant, and its efficient isolation and utilization are challenging owing to the presence of different stereoisomers from various sources. In the present study, a semi-preparative HPLC method for the efficient separation of AST stereoisomers using a Chiralpak IC chiral column with good loading capacity and chiral recognition ability was successfully developed. The mobile phase was methanol-methyl tert-butyl ether (90 : 10, v/v), with a flow rate of 3.06 mL min-1 and a maximum injection volume of 0.32 mg. The results indicated that the purity of all-trans AST was 97.9% for Haematococcus pluvialis and 97.5% for Phaffia rhodozyma. Additionally, molecular weights and fragmentation patterns analyzed using mass spectrometry were consistent with those of all-trans AST. Linearity validation and reproducibility experiments revealed that all calibration curves had coefficients of determination (R2) greater than 0.999 and a relative standard deviation (RSD) of <3.8%. This is because all-trans AST stereoisomers could undergo specific rotations or spins due to π-π interactions, hydrogen bonding, and inclusion interactions. This process allowed the successful separation of the three all-trans AST optical isomers and provides a theoretical basis for large-scale preparation of all-trans AST stereoisomers from different sources.

Devising a computer method to recognize and analyze spectrometric signals parameters

The object of this study is computerized systems for measuring the parameters of spectrometric signals digitized using special hardware. The task addressed in the research is to improve the process of filtering the usable pulse signal from noise and increase the accuracy of measuring pulse parameters by devising a new method of analysis. In order to verify the performance of the new method in comparison with several already known ones, input data arrays with predetermined parameters were prepared using computer simulation. A special algorithm was also developed to verify each detected pulse. As a result, the main characteristics of the methods, such as signal recognition accuracy and data processing speed, were obtained for several scenarios with different durations of modeling process and different pulse generation intensities. Comparative performance metrics were provided for all described software analysis methods. Ultimately, in the studied scenarios, the devised method showed better recognition ability than the considered alternative methods. The key features of the proposed method are the use of software filters built on the basis of the application of Fast Discrete Fourier Transform (FDFT) algorithms and further computer processing of the signal using a mechanism for correcting the amplitudes of superimposed pulses. This makes it possible to filter the signal from noise without significantly changing the usable component and to more accurately determine the amplitudes in case of their frequent superposition. In practice, the devised method could be used to improve existing and design new computer systems of spectral analysis

Recent Progress in Tactile Sensing and Machine Learning for Texture Perception in Humanoid Robotics

ABSTRACTHumanoid robots have garnered substantial attention recently in both academia and industry. These robots are becoming increasingly sophisticated and intelligent, as seen in health care, education, customer service, logistics, security, space exploration, and so forth. Central to these technological advancements is tactile perception, a crucial modality through which humanoid robots exchange information with their external environment, thereby facilitating human‐like behaviors such as object recognition and dexterous manipulation. Texture perception is particularly vital for these tasks, as the surface morphology of objects significantly influences recognition and manipulation abilities. This review addresses the recent progress in tactile sensing and machine learning for texture perception in humanoid robots. We first examine the design and working principles of tactile sensors employed in texture perception, differentiating between touch‐based and sliding‐based approaches. Subsequently, we delve into the machine learning algorithms implemented for texture perception using these tactile sensors. Finally, we discuss the challenges and future opportunities in this evolving field. This review aims to provide insights into the state‐of‐the‐art developments and foster advancements in tactile sensing and machine learning for texture perception in humanoid robotics.

Alexithymia does not explain facial expression recognition difficulties across the dark triad spectrum.

The dark triad encompasses socially aversive personality traits-narcissism, psychopathy, and Machiavellianism-and has been shown to be associated with expression recognition difficulties. Alexithymia has been shown to be associated with the dark triad, and recent evidence has suggested that co-occurring alexithymia may explain facial expression recognition difficulties found in the autism spectrum. Here, I tested this alexithymia hypothesis for individuals on the dark triad spectrum. Using an individual difference approach, I assessed whether trait alexithymia was able to predict unique variance in facial expression discrimination ability and facial expression labelling ability above and beyond an individual's level of dark triad traits. Results showed that autistic traits, alexithymic traits, and dark triad traits all correlated with expression recognition ability. However, linear regression models showed that an individual's level of dark triad traits, their level of autistic traits, and a brief measure of general cognitive ability each predicted unique variance in facial expression discrimination and facial expression labelling ability, but an individual's level of alexithymic traits predicted no additional unique variance. Results suggest that dark triad and autistic traits each contribute to expression recognition ability in unique ways alongside general cognitive ability.

Blending-Based Ensemble Learning Low-Voltage Station Area Theft Detection

In order to improve the efficiency of electricity theft detection, the power theft detection area and users should be better integrated, we proposed a Blending ensemble learning electricity theft detection model based on the Base Learner Selection Strategy (BLSS). Firstly, the adaptive synthetic (ADASYN) sampling method is used to process the unbalanced power consumption data, and the sample distribution of training data is balanced. Secondly, the BLSS selection method is used to screen the optimal base learner combination and construct the Blending ensemble learning model. Then, based on the historical data, the model makes a short-term prediction of the power consumption of the station area the next day, and focuses on the verification of the suspected energy-stealing station area where the Root Mean Square Percentage Error (RSPE) exceeds the threshold, so as to lock in the potential energy stealing users. Finally, through the comparison and verification of real examples, the search scope for electricity theft inspections was reduced by 79.17%, greatly improving the detection efficiency of the power supply company. At the same time, the model’s electricity theft detection and recognition accuracy rate can be as high as 97.50%. The Blending ensemble learning electricity stealing detection model based on the BLSS base learner selection method has strong electricity stealing detection and recognition ability.

Binding of Bioactive Ammonium Ions in Water with a Cavity-Based Selectivity: Water Solubilization versus Micellar Incorporation.

Many bioactive molecules contain primary ammonium groups, generating significant interest in developing selective receptors for ammonium ions. A promising strategy involves the use of polyaromatic cavitands to achieve size and shape selectivity through their cavity. However, designing effective receptors for ammonium ions in aqueous media is challenging due to the competitive nature of water. Calix[5]arenes are known to selectively bind primary ammonium ions over secondary, tertiary, and quaternary ammonium ions in organic solvents. Here, we report on the binding properties of a calix[5]arene, which bears carboxyl groups on its small rim, in organic solvents and aqueous media. This receptor was transferred in water either through deprotonation of its carboxyl groups or by incorporation into dodecylphosphocholine micelles. 1H Nuclear Magnetic Resonance data confirmed the endo complexation of various primary ammonium ions in not only organic solvents but also both aqueous media. Cavity-based selectivity was also observed, validating the cavitand strategy for the selective binding of ammonium ions in water. Unique binding properties, driven by the calix[5]arene's intrinsic recognition ability and the hydrophobic effect, were observed in water. Notably, binding affinities for dopamine and lysine derivatives with log Ka values of >3.9 were determined. The direct solubilization of the receptor outperformed micellar incorporation due to the hydrophilic nature of the primary ammonium ions, which hinders their uptake into micelles. These results offer promising perspectives for the development of efficient chemosensors for the characterization of bioactive ammonium ions in water.

Enhancing CNN Weights for Improved Routing in UAV Networks for Catastrophe Relief with MSBO Algorithm

UAVs have become key in various applications lately, from catastrophe relief to environmental monitoring. The plan of powerful and reliable directing protocols in UAV networks is seriously hampered by the dynamic and habitually eccentric mobility patterns of UAVs. This study proposes a novel technique to beat these challenges by utilizing the Modified Smell Bees Optimization (MSBO) algorithm to upgrade the weights of CNNs. This study’s principal objective is to further develop UAV network routing decisions by using CNNs’ ability for design recognition and the Modified SBO’s optimization abilities. Our methodology comprises of randomly relegating CNN weights to a populace of bees at start, evaluating their wellness by fitness of directing performance, and iteratively fine-tuning these weights utilizing local and global search procedures got from bee searching. Broad simulations and performance evaluations show that our recommended approach incredibly expands the general dependability of UAV’s, brings down communication latency, and improves directing productivity. Future exploration in UAV network improvement gives off an impression of being going in a promising direction with the integration of CNNs for pattern recognition and the Modified SBO for weight enhancement. In addition to progressing UAV routing conventions, this work sets out new open doors for machine learning applications of bio-inspired optimization algorithms.

Self-assembled organic monolayer functionalized MIL-88B for selective acetone detection at room temperature

Acetone detection is crucial for diagnosing diseases such as diabetes and lung cancer. Therefore, it is essential to design a room-temperature acetone gas sensor with fast response and recovery times, high sensitivity, high selectivity, and a low detection limit. However, current acetone gas sensors face challenges in achieving high-selectivity detection at room temperature. This study primarily utilizes self-assembled organic monolayer functionalized MIL-88B to prepare selectivity acetone sensors. The results show that the detection sensitivity of the improved sensor to acetone is significantly improved. Compared with the MIL-88B sensor (0.1 ppm), the response value of the MIL-88B@3-aminopropyltrimethoxysilane (APTMS) sensor is increased by about 61.9%. The response to 10 ppm acetone is 83, and the selectivity is greatly improved at room temperature. This can be attributed to the chemical interactions between acetone molecules and APTMS on the sensor surface, which improves the sensor's specific recognition ability for acetone. Additionally, the sensor exhibits better stability and shorter response and recovery times. Consequently, the APTMS functionalization of MIL-88B presents an effective method for preparing room-temperature acetone sensors, combining high sensitivity and selectivity, and offering potential for non-invasive disease diagnosis.

Polyvalent Aptamers Structure-Mediated Fluorescent Aptasensor for the Early Diagnosis of Alzheimer's Disease by Coupling with HCR and CRISPR-Cas System.

The early diagnosis of Alzheimer's disease (AD) plays a vital role in slowing the progression of AD and improving the quality of human life. However, it is still a challenge in the medical field. Herein, an ultrasensitive fluorescent aptasensor was designed for the detection of special phosphorylated tau181 (P-tau181) by coupling with polyvalent aptamers (PAs) structure, hybridization chain reaction (HCR), and the CRISPR-Cas system. Coupling with the signal amplification strategy, the specific recognition ability of the aptamer, and the high cleavage activity of Cas12a protein, the designed aptasensor showed a wide linear range (0.1-106 pg/mL), a low detection limit (0.069 pg/mL), high selectivity, and excellent anti-interference ability for the detection of P-tau181. Moreover, the aptasensor can efficiently analyze P-tau181 in artificial cerebro spinal fluid (aCSF) and serum, proving that it has a promising application in the early diagnosis of AD.

Peach Leaf Shrinkage Disease Recognition Algorithm Based on Attention Spatial Pyramid Pooling Enhanced with Local Attention Network

Aiming at many challenges in the recognition task of peach leaf shrink disease, such as the diversity of object size of diseased leaf disease, complex background interference, and inflexible adjustment of model training learning rate, we propose a peach leaf shrink disease recognition algorithm based on an attention generalized efficient layer aggregation network. Firstly, the rectified linear unit activation function is used to effectively improve the stability and performance of the model in low-precision computing environments and solve the problem of partial gradient disappearance. Secondly, the integrated squeeze-and-excitation network attention mechanism can adaptively focus on the key areas of pests and diseases in the image, which significantly enhances the recognition ability of the model to the characteristics of pests and diseases. Finally, combined with fast pyramid pooling enhanced with Local Attention Networks, the deep fusion of cross-layer features is realized to improve the ability of the model to identify complex features and optimize the operation efficiency. The experimental results on the peach leaf shrink disease recognition dataset show that the proposed algorithm achieves a significant improvement in performance compared with the original YOLOv8 algorithm. Specifically, mF1, mPrecision, mRecall, and mAP increased by 0.1075, 0.0723, 0.1224, and 0.1184, respectively, which provided strong technical support for intelligent and automatic monitoring of peach pests and diseases.