Recognition Rate Research Articles

E-nose detection of changes in volatile profile associated with early decay of ‘Golden Delicious’ apple by Penicillium expansum

The ability of an electronic nose system to differentiate alterations in the volatile organic compound (VOCs) profile caused by early spoilage of ‘Golden Delicious’ apples due to Penicillium expansum was thoroughly evaluated. Three strains of this mould species (M639, pe2280 and pe2278) were individually used to inoculate ‘Golden Delicious’ apples, resulting in four different batches: (i) M639, (ii) pe2280, (iii) pe2278 and (iv) a control group (inoculated with sterile water). Volatile compounds were identified and quantified by gas chromatography/mass spectrometry (GC/MS), and signals from an electronic nose system (E-nose) were recorded for each batch with three different growth diameters: early stage (10 mm), middle stage (20 mm) and late stage (40 mm). A strong correlation was observed between the responses from multiple E-nose biosensors and the aromatic profile associated with fungal alterations in apples. Using linear discriminant analysis (LDA) models based on E-nose sensor data from the specified batches, we successfully differentiated healthy and infected samples, specifically three distinct groups: control, M639+pe2280 and pe2278. Remarkably, the recognition rates for total external samples exceeded 87% and reached 97% for samples in the early stage of fungal infection. These results validate the online capability of E-nose technology for the non-destructive evaluation of apple storage processes.

Exploring User-Defined Gestures as Input for Hearables and Recognizing Ear-Level Gestures with IMUs

Hearables are highly functional earphone-type wearables; however, existing input methods using stand-alone hearables are limited in the number of commands, and there is a need to extend device operation through hand gestures. In previous research on hearables for hand input, user understanding and gesture recognition systems have been developed. However, in the realm of user understanding, investigation concerning hand input with hearables remains incomplete, and existing recognition systems have not demonstrated proficiency in discerning user-defined gestures. In this study, we conducted a gesture elicitation study (GES) assuming hand input using hearables under six conditions (three interaction areas x two device shapes). Then, we extracted ear-level gestures that the device's built-in IMU sensor could recognize from the user-defined gestures and investigated the recognition performance. The results of sitting experiments showed that the gesture recognition rate for in-ear devices was 91.0% and that for ear-hook devices was 74.7%.

Vibration displacement measurement of bridge structural models using image super-resolution reconstruction and visual object detection network

Abstract Visual vibration measurement has emerged in the field of structural health monitoring in recent years, but it still has some shortcomings in terms of resolution, recognition rate and real-time performance. Considering the three aspects of recovering high-frequency image details, improving the compactness of the target bounding box, and reducing the computational time, we use the constructed image super-resolution reconstruction model and target detection model to measure the vibration displacement of the bridge structural model. First, we integrate the Transformer module into the Unet network with a simple structure. The Swin and Global Transformer Unet (SGTU) module constructed in this form can reduce the computational cost while reconstructing the large-resolution feature map target, and it can sharply edge information of the vibration target. We use the framework of the YOLOv5 algorithm as the backbone, and use the GhostBottleneck (GB) module to reduce the time for convolution operations to generate similar features. In addition, the proposed DWCBottleneck (DWCB) fusion module is also able to achieve high-level semantic fusion and network depth expansion with minimal computational cost. Finally, the center point offset of the bounding box predicted by the model can be used to obtain the displacement offset of the object in the image sequence. The position information of the target in the first frame image is used as the reference frame for calculating the offset, and the vibration displacement of the flexible structure in the image coordinate system is obtained by calculating the deviation of the displacement between the remaining frames and the first frame. We perform qualitative and quantitative comparisons in three aspects: video super-resolution reconstruction, visual detection robustness, and sensor vibration measurement displacement using a homemade vibration image dataset. The time-frequency domain displacement curves regressed by the visual vibration measurement algorithm are compared with the curves acquired after accelerometer acquisition, indicating the necessity of super-resolution reconstruction in visual vibration measurement.

Tone classification of online medical services based on 1DCNN-BiLSTM

In order to improve the recognition rate of the tone classification of doctors in online medical services scenarios, we propose a model that integrates a one-dimensional convolutional neural network (1DCNN) with a bidirectional long short-term memory network (BiLSTM). Firstly, significant tone types within online medical services scenarios were identified through a survey questionnaire. Secondly, 68 features in both the time and frequency domains of doctors’ tone were extracted using Librosa, serving as the initial input for the model. We utilize the 1DCNN branch to extract local features in the time and frequency domains, while the BiLSTM branch captures the global sequential features of the audio, and a feature-level fusion is performed to enhance tone classification effectiveness. When applied in online medical services scenarios, experimental results show that the model achieved an average recognition rate of 84.4% and an F1 score of 84.4%, significantly outperforming other models and effectively improving the efficiency of doctor-patient communication. Additionally, a series of ablation experiments were conducted to validate the effectiveness of the 1DCNN and BiLSTM modules and the parameter settings.

CNN MODEL FOR TRAFFIC SIGN RECOGNITION

The traffic sign recognition framework (TSRS) is an important component of intelligent transportation systems (ITS). Accurately identifying traffic signs can improve driving safety. This research provides a traffic sign recognition approach based on profound learning. It primarily focuses on the location and order of roundabout signs. First, a photograph undergoes pre-processing to highlight important facts. Hough Transform is used to distinguish and find regions. Finally, the unique street traffic signs are analyzed for further understanding. This paper proposes a photo handling-based traffic sign discovery and distinguishing proof technique that is combined with convolutional brain organization (CNN) to sort traffic signs. CNN is useful for recognizing many PC vision tasks due to its high recognition rate. TensorFlow is used to implement CNN. We have a recognition accuracy of over 98.2% for the roundabout image in the German informative collections. KEYWORDS——traffic sign recognition, traffic sign detection, deep learning, convolutional neural network

Impaired facial emotion recognition in individuals with bipolar disorder

BackgroundIndividuals with bipolar disorder (BD) often struggle with emotional regulation and social interactions, partly due to difficulties in accurately recognizing facial emotions. MethodsFrom September 2021 to February 2023, 69 BD individuals-comprising 23 with bipolar manic/hypomanic episode (BME), 23 with bipolar depressive episode (BDE), 23 with bipolar euthymic (EUT)-and 23 healthy controls (HCs) were enrolled. Diagnosis adhered to DSM-IV criteria using M.I.N.I 5.0, alongside assessments via Hamilton Depression Scale 17 and Young Manic Rating Scale. Recognition tasks involving 84 facial expression images across six categories. The Wilcoxon rank-sum test compares two groups, while the Kruskal-Wallis test compares multiple groups with subsequent adjusted pairwise comparisons. ResultsThe overall correct recognition rate of facial expressions in the BD group (79 %) was significantly lower than that of the HC group (83 %) (P=0.004). Primary differences were noted in neutral (93 % vs. 100 %, P=0.012) and fear (79 % vs. 86 %, P=0.023) expressions. Within the BD group, correct recognition rates were 71 % for BME, 80 % for BDE, and 80 % for EUT, all lower than in the HC group. Significant differences in correct recognition rates of neutral, fear, and joy expressions were observed among the four groups (P<0.05), with the BME group exhibiting the lowest rate. Misidentification of facial expressions was more frequent in the BD group compared to the HC group, particularly among negative expressions. ConclusionPatients with BD demonstrate lower correct recognition and higher misidentification rates of facial expressions, with those experiencing manic episodes showing impaired recognition of neutral, joy, and fear expressions.

Implementation of sprinkling location with restructure-monochrome-dot on diffusivity mutational-status of fabricated function agent on porous

The recognition technology that determines the sprinkling mutation status in simple squamous epithelium cells produces a monochromatic dot pattern in an echo state using the instantaneous recognition rate (MPR) and vacuum recognition rate (VPR). The diffusivity echo system was created in the form of sprinkler recognition to control recognition rate conditions. The mutation status of simple squamous epithelium cells is displayed as a sprinkling porous value according to the sprinkling location layer by a diffusivity-down structure to search as a jagged monochrome-dot pattern. In the sprinkling porous, the perception rate concept is verified by referencing the instantaneous rate and vacuum rate to the mutant state signal through the sprinkling echo conformation. The jagged mutation state of MPR-VPR appears from a sprinkling porous to a maximum-minimum sprinkling-echo conformation. Sprinkling echo locations are found in the sprinkling porous values of the mutant state. Wr-af-FA-τMED is far mutational-status of 18.12±5.16 units, Wr-af-CO-τMED is convenient mutational-status of 6.89±0.30 units, Wr-af-FL-τMED is flank mutational-status of 2.34±1.53 units, Wr-af-VI-τMED is vicinage mutational-status of 0.48±0.20 units. Diffusivity echo calculates the jagged momentary vacuum conformation that appears through the perception rate system in simple squamous epithelium cells, and the ability to estimate the sprinkling-echo conformation for the jagged degree perception rate of MPR-VPR can be confirmed. We can estimate the shape through the vacuum signal in the sprinkling porous and estimate the diffusion data of the diffusivity echo rate through the diffusivity perception system.

Multimodal Emotion Recognition Based on Facial Expressions, Speech, and Body Gestures

The research of multimodal emotion recognition based on facial expressions, speech, and body gestures is crucial for oncoming intelligent human–computer interfaces. However, it is a very difficult task and has seldom been researched in this combination in the past years. Based on the GEMEP and Polish databases, this contribution focuses on trimodal emotion recognition from facial expressions, speech, and body gestures, including feature extraction, feature fusion, and multimodal classification of the three modalities. In particular, for feature fusion, two novel algorithms including supervised least squares multiset kernel canonical correlation analysis (SLSMKCCA) and sparse supervised least squares multiset kernel canonical correlation analysis (SSLSMKCCA) are presented, respectively, to carry out efficient facial expression, speech, and body gesture feature fusion. Different from the traditional multiset kernel canonical correlation analysis (MKCCA) algorithms, our SLSKMCCA algorithm is a supervised version and is based on the least squares form. The SSLSKMCCA algorithm is implemented by the combination of SLSMKCCA and a sparse item (L1 Norm). Moreover, two effective solving algorithms for SLSMKCCA and SSLSMKCCA are presented in addition, which use the alternated least squares and augmented Lagrangian multiplier methods, respectively. The extensive experimental results on the popular public GEMEP and Polish databases show that the recognition rate of multimodal emotion recognition is superior to bimodal and monomodal emotion recognition on average, and our presented SLSMKCCA and SSLSMKCCA fusion methods both obtain very high recognition rates, especially for the SSLSMKCCA fusion method.

Benefits of speech recognition in noise using remote microphones for people with typical hearing

IntroductionRemote microphone (RM) systems are designed to enhance speech recognition in noisy environments by improving the signal-to-noise ratio (SNR) for individuals with typical hearing (TH) and hearing impairment (HI). The aim of this investigation was to evaluate the advantages of speech recognition in noise for individuals with TH in a simulated group setting using two different remote microphones. MethodsA quasi-experimental, repeated-measures design was employed, involving ten participants with TH, ages 20 to 63 years. Each were fit with Roger Focus receivers bilaterally to listen to three RM conditions: Roger Select, Roger Pen, and no technology. Participants were instructed to transcribe sentences that were presented randomly at varying signal-to-noise ratios (SNRs: 0, -5, and -10 dB) from five speakers positioned equidistant around a circular table to simulate a group dining scenario. ResultsSignificant main effects of the technology condition and noise level (p < .05) were found. Participants exhibited superior performance with Roger Select compared to Roger Pen. As expected, recognition rates decreased with lower SNRs across all three technology conditions. ConclusionsTo enhance speech recognition in group settings for individuals with TH, the utilization of the Roger Select microphone in conjunction with bilateral Roger Focus receivers is recommended over the Roger Pen

License Plate Recognition Using Three-Dimensional Rotated Character Recognition and Instance Segmentation by Deep Learning

License plate recognition is currently used in various situations, such as parking lot vehicle management and the tracking of wanted vehicles. These applications require recognition from all possible camera angles. Therefore, we propose a method for license plate recognition in images captured from various camera angles. First, the license plate area is detected from the input image using the YOLOv5 object detection method. The subsequent process can be performed in two manners: by rotating the license plate to the front using projective transformation and trapezoidal correction, or by using graph matching. The first method performs Hough transforms or linear approximations as preprocessing, and then calculates the rectangle surrounding the license plate from the YOLOv5 output. After performing trapezoidal correction, the maximally stable extremal regions (MSER) are used to detect character candidates, and characters are recognized using 3D rotated character recognition. The second method performs character candidate detection and recognition without trapezoidal correction, followed by graph matching. These methods are versatile because they do not depend on the layout of license plates, which varies among countries and regions. Two types of datasets were used: a set of images containing Japanese license plates collected by ourselves, and a set of publicly available images containing Taiwanese license plates. Two recognition rates were evaluated: the license plate character recognition rate and license plate recognition rate in which all characters in one plate are recognized. The license plate character recognition rates using graph matching were 91.9% for the Japanese license plates and 89.3% for the Taiwanese license plates. The license plate recognition rates were 84.0% and 84.5%, respectively.

Recognition of car horns based on principal component analysis of MEL frequency Cepstral coefficients and support vector machine

With the rapid increase in the number of automobiles, the noise pollution caused by car horns is attracting more attention. In order to accurately identify car horn sounds in traffic noise and strengthen traffic law enforcement, research on car horn sound recognition is becoming increasingly important. In this paper, using Principal Component Analysis (PCA) to optimize and reduce the dimensionality of extracted Mel Frequency Cepstral Coefficients (MFCC), feature vectors are input into four models: Support Vector Machine (SVM), Back Propagation (BP) Neural Network, Extreme Learning Machine (ELM), and Random Forest (RF). These models are utilized to classify and identify car horn sounds from traffic noise. The impact of feature dimensions and Signal-to-noise ratio(SNR) on recognition performance is analyzed. The results show that under this method, the recognition rates of the four models can be increased by increasing the number of Mel filters and feature dimensions in MFCC, which can improve recognition performance, especially when the SNR is lower. The SVM model exhibits the most significant improvement in recognition rate. They achieve the best recognition rates for measured car horn sounds of 98.66 %, 93.98 %, 89.44 %, and 95.12 %, respectively. Experimental results demonstrate that the proposed method has good recognition performance and can be effectively applied to the supervision of car horn usage on actual roads.

Method for Augmenting Side-Scan Sonar Seafloor Sediment Image Dataset Based on BCEL1-CBAM-INGAN.

In this paper, a method for augmenting samples of side-scan sonar seafloor sediment images based on CBAM-BCEL1-INGAN is proposed, aiming to address the difficulties in acquiring and labeling datasets, as well as the insufficient diversity and quantity of data samples. Firstly, a Convolutional Block Attention Module (CBAM) is integrated into the residual blocks of the INGAN generator to enhance the learning of specific attributes and improve the quality of the generated images. Secondly, a BCEL1 loss function (combining binary cross-entropy and L1 loss functions) is introduced into the discriminator, enabling it to focus on both global image consistency and finer distinctions for better generation results. Finally, augmented samples are input into an AlexNet classifier to verify their authenticity. Experimental results demonstrate the excellent performance of the method in generating images of coarse sand, gravel, and bedrock, as evidenced by significant improvements in the Frechet Inception Distance (FID) and Inception Score (IS). The introduction of the CBAM and BCEL1 loss function notably enhances the quality and details of the generated images. Moreover, classification experiments using the AlexNet classifier show an increase in the recognition rate from 90.5% using only INGAN-generated images of bedrock to 97.3% using images augmented using our method, marking a 6.8% improvement. Additionally, the classification accuracy of bedrock-type matrices is improved by 5.2% when images enhanced using the method presented in this paper are added to the training set, which is 2.7% higher than that of the simple method amplification. This validates the effectiveness of our method in the task of generating seafloor sediment images, partially alleviating the scarcity of side-scan sonar seafloor sediment image data.

AI-RCAS: A Real-Time Artificial Intelligence Analysis System for Sustainable Fisheries Management

This study proposes an Artificial Intelligence-based Real-time Catch Analysis System (AI-RCAS) for sustainable fisheries management. The AI-RCAS, implemented on a Jetson board, consists of fish recognition using YOLOv10, tracking with a ByteTrack algorithm optimized for marine environments, and a counting module. Experiments in actual fishing environments showed significant improvements, with species recognition rates of 74–81%. The system supports the efficient operation of the total allowable catch (TAC) system through real-time analysis, addressing the limitations of the existing Electronic Monitoring (EM) systems. However, challenges remain, including object-tracking difficulties and performance issues in unstable marine environments. Future research should focus on optimizing the fishing process, improving video processing, and expanding the dataset for better generalization.

Target Recognition Based on Infrared and Visible Image Fusion and Improved YOLOv8 Algorithm.

In response to the issue that the fusion process of infrared and visible images is easily affected by lighting factors, in this paper, we propose an adaptive illumination perception fusion mechanism, which was integrated into an infrared and visible image fusion network. Spatial attention mechanisms were applied to both infrared images and visible images for feature extraction. Deep convolutional neural networks were utilized for further feature information extraction. The adaptive illumination perception fusion mechanism is then integrated into the image reconstruction process to reduce the impact of lighting variations in the fused images. A Median Strengthening Channel and Spatial Attention Module (MSCS) was designed to be integrated into the backbone of YOLOv8. In this paper, we used the fusion network to create a dataset named ivifdata for training the target recognition network. The experimental results indicated that the improved YOLOv8 network saw further enhancements of 2.3%, 1.4%, and 8.2% in the Recall, mAP50, and mAP50-95 metrics, respectively. The experiments revealed that the improved YOLOv8 network has advantages in terms of recognition rate and completeness, while also reducing the rates of false negatives and false positives.

FM‐YOLOv8:Lightweight gesture recognition algorithm

AbstractIn practical production applications, the efficiency and success rate of gesture recognition directly affect the user experience and work efficiency. However, the existing gesture recognition models have the problem of a large number of model parameters and high computational complexity, which makes them unable to meet the needs of end‐to‐end industrial deployment. To solve these problems, this article proposes a gesture recognition model based on YOLOv8. First, FasterNet is adopted as the backbone of YOLOv8, which significantlydecrease the number of parameters and made the model more lightweight. By reducing the number of parameters, the computational complexity of the model can be reduced while maintaining the performance of the model, and the operation efficiency of the model can be improved. Second, recombination convolution ScConv is introduced to replace common convolution operations to further improve the model's efficiency. Recombination convolution can reduce the computation and make up for the loss of precision to some extent. Finally, the MDPIoU loss function is used to optimize target location and prediction, to improve the accuracy of the model. The MDPIoU loss function can better deal with the problem of target boundary frame positioning and prediction so that the model can locate and predict gestures more accurately in gesture recognition tasks. Experiments on a data set containing 10 types of gestures show that the number of parameters and floating point calculations of the improved network model are reduced by 45% and 42.7%, respectively, while the accuracy is unchanged. The improved model can be deployed on edge terminals, providing efficient and accurate gesture recognition.

Proton-gated organic thin-film transistors for leaky integrate-and-fire convolutional spiking neural networks

Artificial spiking neurons, integral to the functionality of spiking neural networks, are designed to mimic the information transmission via discrete spikes in biological nervous systems. Traditional approaches that necessitate the charging of capacitors and the inclusion of discharge circuits for neuron membrane potential integration and leakage, present challenges in terms of cost and space efficiency. To overcome the challenges, this work proposes a hardware leaky integrate-and-fire neuron based on organic thin-film transistors. Under the electric field, the ion dynamics in the gate electrolyte can mimic the processes of membrane potential integration, leakage, and reset in spiking neurons. The convolutional spiking neural networks composed of such organic spiking neurons achieves excellent recognition rates (∼97.26 %) on the MNIST dataset. This indicates that the organic spiking neuron has enormous potential in next-generation non-von Neumann neuromorphic computing.

Adulteration detection of multi-species vegetable oils in camellia oil using Raman spectroscopy: Comparison of chemometrics and deep learning methods

Oil adulteration is a global challenge in the production of high value-added natural oils. Raman spectroscopy combined with mathematical modeling can be used for adulteration detection of camellia oil (CAO). In this study, the advantages of traditional chemometrics and deep learning methods in identifying and quantifying adulterated CAO were compared from a statistical perspective, and no significant difference were founded in the identification of CAO at different levels of adulteration. The recognition rate of pure and adulterated CAO was 100 %, but there were misclassifications among different adulterated CAOs. The deep learning models outperformed chemometrics methods in quantitative prediction of adulteration level, with RP2, RMSEP, and RPD of the optimal ConvLSTM model achieved 0.999, 0.9 % and 31.5, respectively. The classifiers and models developed in this study based on deep learning have wide applicability and reliability, and provide a fast and accurate method for adulteration detection in CAO.

Method for enhanced gesture recognition under low light conditions based on wearable mechanoluminescence sensors

Gestures, as one of the key modes of human–computer interaction, are currently identified and processed mainly through two methods: machine vision imaging and wearable stress/strain sensing.However, the former has high requirements for lighting and background.This paper innovatively proposes a feature fusion algorithm that combines mechanoluminescent sensors for gesture recognition under low-light conditions. Unlike existing methods, this algorithm creates a system that integrates mechanoluminescent sensors for visual gesture recognition. By triggering the sensor’s luminescence through mechanical stress, it provides additional light source information to enhance image quality in low-light environments.For this purpose, this study employed the fluorescent emission properties of ZnS:Cu to fabricate a mechanoluminescence sensor. Its mechanoluminescence response characteristics were measured. Based on these findings, an algorithm for the fusion of gesture information features was developed for low illumination backgrounds. This algorithm decomposes the gesture visual images through YCbCr, extracting the HOG features of the Cr channel (Cr-HOG). Simultaneously, feature fusion is performed using the pooling layer (VGG16-Conv5-pool) following the convolutional layer (Conv5-3) in the VGG16 model. A one-to-one composite SVM classifier is constructed to complete the training and testing of the gesture recognition model. Ultimately, the feasibility of this enhanced gesture recognition method was validated through unmanned vehicle control experiment. Experimental results demonstrated that in environments with an illuminance level below 10 LUX measured by a light meter, the average recognition rate of the wearable mechanoluminescence sensor feature fusion algorithm reached 95.82 %. This is 32.24 % higher than the recognition rate of the single Cr-HOG feature classification and 28.27 % higher than the single VGG16-Conv5-pool feature classification. Compared with feature extraction using ResNet-50 and DenseNet-121 networks, the recognition rate for classifying gestures under low-light conditions is approximately 30 % higher.Compared with other image enhancement recognition methods, the recognition can be increased by up to 30.88 %.

Research on Welding Defect Classification Methods Based on Convolutional Neural Networks

To address the issues of low detection and identification rates and inaccurate classification of welding defects, this paper proposes a welding defect classification method based on convolutional neural networks. By modifying the ResNet101 backbone network and incorporating a multi-head attention mechanism (MHA), the method enhances the focus on regions of interest in welding defect images, thereby improving the ability to extract defect features. This approach reduces the chances of missed detections and false positives. By analyzing the effects of different optimizers and dynamic factors on recall (M) and precision (N), the optimal optimizer and dynamic factor are identified. The algorithm is validated on the JPEGWD dataset. Experimental results show that the recall (M) reaches 0.9634, representing a 4.88% improvement, and the precision (N) reaches 0.9875, representing a 3.81% improvement. The mean average precision (mAP) is 0.9817, reflecting a 5.98% improvement. These results effectively enhance the recognition rate of welding defects and reduce the probability of missed detections and false positives.

Moisture-wicking Janus-structure electronic knitted fabric for multimodal wearable mechanical sensing

Multimodal mechanical sensors that can recognize bending direction and exhibit excellent wearable performance are crucial for the fields of physical exercise and healthcare. This study fabricated a knitted multimodal sensor with porous and wetting gradients using hydrophobic core-spun yarns and hydrophilic CNT/WPU conductive yarns in plain stitch and partial tuck stitch. The electronic fabric demonstrated reliable strain sensing unaffected by compression disturbances and displayed a selective response to directional bending. The sensor exhibits a 50% sensing range with a GFmax of −4.41 during strain deformation detection. In terms of bending detection, one side achieves a 10% sensing range (−51.68°) with a GFmax of −6.89, while the other side achieves a 20% sensing range (73.72°) with a GFmax of 8.64. Encouragingly, deep learning incorporated with the sensor achieves an impressive recognition rate of 98.16% for mixed signals with different force levels. Furthermore, it possesses excellent wearable properties such as breathability, moisture permeability, perspiration remove, quick-drying and washability, suitable for applications like activity monitoring, medical rehabilitation evaluation, and gesture recognition. This work presents a promising pathway for the advancement of next-generation multifunctional electronic textiles.