High Recognition Accuracy Research Articles

Human Gait phases recognition based on multi-source data fusion and BILSTM attention neural network

A human gait recognition algorithm with deep learning based on multi-source data fusion is proposed to assist exoskeleton realizing complex human-exoskeleton cooperative motion. A lightweight gait acquisition device simultaneously acquires three different types of sensor signals, i.e., thigh surface electromyography (sEMG), ground reaction force (GRF) of human feet and two joints motion information. The sample data is obtained by many multi-scene gait experiments involving stand still, walk up/down stairs, and walk up/down slope, etc. The proposed algorithm recognizes multiple gait phases (27 classes) in different motion patterns by using short-time gait data, which has two typical advantages: (1) Based on multi-source sensor distributed in human body, this wearable device is constructed for ease of use to address several Subjects (different weights and heights) with low cost and light weight. (2) The critical features of gait data are identified by Bi-directional Long Short-Term Memory (BILSTM) attention neural network with higher recognition accuracy than other state-of-art recognition methods, especially in arbitrary gait switching durations.

A tactile sensing system capable of recognizing objects based on bioinspired self-sensing soft pneumatic actuator

Tactile sensors play an important role when robots perform contact tasks, such as physical information collection, force or displacement control to avoid collision. For these manipulations, excessive contact may cause damage while poor contact cause information loss between the robotic end-effector and the objects. Inspired by skin structure and signal transmission method, this paper proposes a tactile sensing system based on the self-sensing soft pneumatic actuator (S-SPA) capable of providing tactile sensing capability for robots. Based on the adjustable height and compliance characteristics of the S-SPA, the contact process is safe and more tactile information can be collected. And to demonstrate the feasibility and advantage of this system, a robotic hand with S-SPAs could recognize different textures and stiffness of the objects by touching and pinching behaviours to collect physical information of the various objects under the positive work states of the S-SPA. The result shows the recognition accuracy of the fifteen texture plates reaches 99.4%, and the recognition accuracy of the four stiffness cuboids reaches 100%by training a KNN model. This safe and simple tactile sensing system with high recognition accuracies based on S-SPA shows great potential in robotic manipulations and is beneficial to applications in domestic and industrial fields.

Increasing Offline Handwritten Chinese Character Recognition Using Separated Pre-Training Models: A Computer Vision Approach

Offline handwritten Chinese character recognition involves the application of computer vision techniques to recognize individual handwritten Chinese characters. This technology has significantly advanced the research in online handwriting recognition. Despite its widespread application across various fields, offline recognition faces numerous challenges. These challenges include the diversity of glyphs resulting from different writers’ styles and habits, the vast number of Chinese character labels, and the presence of morphological similarities among characters. To address these challenges, an optimization method based on a separated pre-training model was proposed. The method aims to enhance the accuracy and robustness of recognizing similar character images by exploring potential correlations among them. In experiments, the HWDB and Chinese Calligraphy Styles by Calligraphers datasets were employed, utilizing precision, recall, and the Macro-F1 value as evaluation metrics. We employ a convolutional self-encoder model characterized by high recognition accuracy and robust performance. The experimental results demonstrated that the separated pre-training models improved the performance of the convolutional auto-encoder model, particularly in handling error-prone characters, resulting in an approximate 6% increase in precision.

Intelligent Acoustic and Optical Anomaly Monitoring System for Expressway Tunnels Based on the Internet of Things

A smart sound and light anomaly monitoring system for highway tunnels based on Internet of Things technology was studied to address the issues of highway tunnel lighting systems. By utilizing Internet of Things technology, the tunnel lighting system is combined with abnormal sound recognition. Through the design of algorithm models, the recognition of abnormal sound inside the tunnel and the intelligent control of the lighting system is achieved. By pruning and validating the hidden layer nodes of the model, a more streamlined abnormal sound recognition model is obtained. Through experimental verification, this model has the highest recognition accuracy among all models, with a recognition rate of 91.75% at a compression rate of 20%. Compared with Average Percentage of Zeros (APoZ), Random Pruning and Mean Activation, the recognition rate is increased by 2.64%, 1.47% and 1.40%, respectively. In the design of tunnel lighting, fuzzy control is applied to the lighting inside the tunnel to improve the driving safety of drivers and further reduce the power consumption of excessive lighting in the tunnel. Through experiments, it has been proven that the system can work well, saving up to 727[Formula: see text] of energy per day.

Few-shot bearing fault diagnosis by semi-supervised meta-learning with graph convolutional neural network under variable working conditions

Aiming at the problems of low accuracy and weak generalization ability in fault diagnosis caused by complex working conditions and limited fault samples of bearings, a few-shot bearing fault diagnosis method by semi-supervised meta-learning with simplifying graph convolutional neural network (semi-meta-sgc) is proposed. Firstly, the time domain signal is converted into the frequency domain by fast Fourier transform (FFT). Secondly, considering each spectrum sample as a node, a k-nearest neighbor (KNN) graph is constructed according to the adjacencies between nodes, thus transforming the bearing fault classification into a graphical node classification. Then, relying on meta-learning, graph convolutional neural network, and semi-supervised learning, a high-accuracy node classifier is obtained by using a small number of training samples to achieve the classification of bearing faults under variable working conditions. Finally, the proposed method is verified by four cases and compared with other methods. The results show that this method has higher recognition accuracy and generalization performance.

Domestic Cats Facial Expression Recognition Based on Convolutional Neural Networks

Despite extensive research on Facial Expression Recognition (FER) in humans using deep learning technology, significantly less focus has been placed on applying these advancements to recognize facial expressions in domestic animals. Recognizing this gap, our research aims to extend FER techniques specifically to domestic cats, one of the most popular domestic pets. In this paper, we present a real-time system model that employs deep learning to identify and classify cat facial expressions into four categories: Pleased, Angry, Alarmed, and Calm. This innovative model not only helps cat owners understand their pets' behavior more accurately but also holds substantial potential for applications in domestic animal health services. By identifying and interpreting the emotional states of cats, we can address a critical need for improved communication between humans and their pets, fostering better care and well-being for these animals. To develop this system, we conducted extensive experiments and training using a diverse dataset of cat images annotated with corresponding facial expressions. Our approach involved using convolutional neural networks (CNNs) to analyze and learn from the subtleties in feline facial features by investigating the models' robustness considering metrics such as accuracy, precision, recall, confusion matrix, and f1-score. The experimental results demonstrate the high recognition accuracy and practicality of our model, underscoring its effectiveness. This research aims to empower pet owners, veterinarians, and researchers with advanced tools and insights, ensuring the well-being and happiness of domestic cats. Ultimately, our work highlights the potential of FER technology to significantly enhance the quality of life for cats by enabling better understanding and more responsive care from their human companions

Efficient Mixed-Type Wafer Defect Pattern Recognition Based on Light-Weight Neural Network.

Wafer defect pattern recognition can help engineers improve the production process of semiconductor chips. In real industrial scenarios, the recognition of mixed-type wafer defects is difficult and the production scale of semiconductor wafers is large, which requires high accuracy and speed in wafer defect pattern recognition. This study proposes a light-weight neural network model to efficiently recognize mixed-type wafer defects. The proposed model is constructed via inverted residual convolution blocks with attention mechanisms and large kernel convolution downsampling layers. The inference speed of the inverted residual convolution block is fast, and the attention mechanism can enhance feature extraction capabilities. Large kernel convolutions help the network retain more important feature information during downsampling operations. The experimental results on the real Mixed-type WM38 dataset show that the proposed model achieves a recognition accuracy of 98.69% with only 1.01 M parameters. Compared with some popular high-performance models and light-weight models, our model has advantages in both recognition accuracy and inference speed. Finally, we deploy the model as a TensorRT engine, which significantly improves the inference speed of the model, enabling it to process more than 1300 wafer maps per second.

Multi-Feature Fusion Recognition and Localization Method for Unmanned Harvesting of Aquatic Vegetables

The vision-based recognition and localization system plays a crucial role in the unmanned harvesting of aquatic vegetables. After field investigation, factors such as illumination, shading, and computational cost have become the main difficulties restricting the identification and positioning of Brasenia schreberi. Therefore, this paper proposes a new lightweight detection method, YOLO-GS, which integrates feature information from both RGB and depth images for recognition and localization tasks. YOLO-GS employs the Ghost convolution module as a replacement for traditional convolution and innovatively introduces the C3-GS, a cross-stage module, to effectively reduce parameters and computational costs. With the redesigned detection head structure, its feature extraction capability in complex environments has been significantly enhanced. Moreover, the model utilizes Focal EIoU as the regression loss function to mitigate the adverse effects of low-quality samples on gradients. We have developed a data set of Brasenia schreberi that covers various complex scenarios, comprising a total of 1500 images. The YOLO-GS model, trained on this dataset, achieves an average accuracy of 95.7%. The model size is 7.95 MB, with 3.75 M parameters and a 9.5 GFLOPS computational cost. Compared to the original YOLOv5s model, YOLO-GS improves recognition accuracy by 2.8%, reduces the model size and parameter number by 43.6% and 46.5%, and offers a 39.9% reduction in computational requirements. Furthermore, the positioning errors of picking points are less than 5.01 mm in the X direction, 3.65 mm in the Y direction, and 1.79 mm in the Z direction. As a result, YOLO-GS not only excels with high recognition accuracy but also exhibits low computational demands, enabling precise target identification and localization in complex environments so as to meet the requirements of real-time harvesting tasks.

Research on Intelligent Recognition for Plant Pests and Diseases Based on Improved YOLOv8 Model

Plant pests and diseases are important parts of insect disease control and the high-quality development of agriculture. Traditional methods for identifying plant diseases and pests suffer from low accuracy and slow speed, while the existing machine learning methods are constrained by environmental and technological factors, leading to low recognition efficiency. To address the issue of the above problems, this paper has proposed an intelligent recognition algorithm based on the improved YOLOv8 model, which has high recognition accuracy and speed. Firstly, in the Backbone network, the Global Attention Mechanism (GAM) is adopted to weigh the important feature information, thereby improving the accuracy of the model. Secondly, in the mixed feature part of the Neck network, the Receptive-Field Attention Convolutional (RFA Conv) operation is used instead of standard convolution operations to enhance the processing ability for feature information and to reduce computational complexity and costs, thus improving the network performance. After verifying the rice and cotton datasets, the accuracy indicator mean average precision (mAP) reaches 71.27% and 82.91%, respectively, in the two different datasets. Comparing these indices with those of the Faster R-CNN, YOLOv7, and the original YOLOv8 model, the results fully demonstrate the effectiveness and superiority of the improved model in terms of detection accuracy.

In2O3/ZnO heterojunction thin film transistor for high recognition accuracy neuromorphic computing and optoelectronic artificial synapses

Solid electrolyte-gated transistors exhibit improved chemical stability and can fulfill the requirements of microelectronic packaging. Typically, metal oxide semiconductors are employed as channel materials. However, the extrinsic electron transport properties of these oxides, which are often prone to defects, pose limitations on the overall electrical performance. Achieving excellent repeatability and stability of transistors through the solution process remains a challenging task. In this study, we propose the utilization of a solution-based method to fabricate an In2O3/ZnO heterojunction structure, enabling the development of efficient multifunctional optoelectronic devices. The heterojunction’s upper and lower interfaces induce energy band bending, resulting in the accumulation of a large number of electrons and a significant enhancement in transistor mobility. To mimic synaptic plasticity responses to electrical and optical stimuli, we utilize Li+-doped high-k ZrO x thin films as a solid electrolyte in the device. Notably, the heterojunction transistor-based convolutional neural network achieves a high accuracy rate of 93% in recognizing handwritten digits. Moreover, our research involves the simulation of a typical sensory neuron, specifically a nociceptor, within our synaptic transistor. This research offers a novel avenue for the advancement of cost-effective three-terminal thin-film transistors tailored for neuromorphic applications.

Evaluation of the efficiency and accuracy of the system for collecting and processing EMG signals obtained using a bracelet

The object of research is a bracelet that uses the electromyography (EMG) method to control a bionic prosthesis. In the conditions of the development of modern biomedical technologies and robotics, such a system becomes key to improving the quality of life of people with disabilities, providing efficient and accurate control of prostheses. The problem addressed in the research is the development and analysis of a bionic prosthesis control system using a bracelet using the EMG method. The main focus is on the optimization of data collection and processing processes, as well as the development of machine learning algorithms for gesture recognition in order to improve the accuracy and efficiency of prosthetic control. The essence of the obtained results is the development and testing of a new bionic prosthesis control system that uses EMG signals obtained with the help of a bracelet. The study showed that the classifier based on the support vector method outperforms other algorithms such as neural networks and decision trees, achieving an average accuracy of 90 %. The obtained data were successfully filtered and subjected to feature extraction, which allowed to create effective gesture recognition algorithms. The system was tested in real time, which confirmed its high accuracy and efficiency. The proposed system includes an innovative bracelet for collecting EMG data, which are then processed and analyzed using modern machine learning algorithms. The innovativeness of the proposed approach lies not only in the high accuracy of gesture recognition, but also in the possibility of adapting the system to different types of bionic prostheses and operating conditions. This is achieved by using a classifier based on the support vector method, which demonstrates significantly higher accuracy compared to other algorithms such as neural networks and decision trees. The test results show an average accuracy of 92.5 %, which confirms the high efficiency of the system. The use of this system involves the intensive use of EMG sensors, which allows more accurate determination of the user's intentions regarding the control of the prosthesis. This, in turn, contributes to the improvement of the quality of life of users, providing them with greater functionality and convenience in the use of bionic prostheses.

Skin-like n-type stretchable synaptic transistors with low energy consumption and highly reliable plasticity for brain-inspired computing

Artificial synaptic devices with high transconductance, low energy consumption and good stretchability are important for efficient and energy-friendly neuromorphic computations in the field of bionics. Here, we propose a stretchable substrate inspired by wrinkled surface of human skin, and achieve a low energy operation stretchable synaptic transistor (SST) based on n-type oxide semiconductor. The SSTs exhibit excellent performance, including high mobility (4.08 cm2V−1s−1) and high transconductance (over 12 mS) under ultra-low operation voltage of 0.1 V. They can stand against multi-directional stretching of 10 % and up to 400 stretch/release cycles. In addition, the n-type SSTs achieve synaptic performance at ultra-low energy consumption (0.36 fJ) with dual-mode operation characteristics of excitatory and inhibitory behaviors. Under tensile strain, they exhibit typical synaptic behavior, including short-term/long-term plasticity, pair pulse facilitation, spike voltage/frequency/duration/number-dependent plasticity. More importantly, the SSTs exhibit excellent “learning-forgetting-relearning” feature and good stability under potentiation-depression cycle test, showcasing tremendous potential in brain-inspired computation. Finally, a high recognition accuracy (89.6 %) is attained simulated by handwritten digital datasets. To the best of our knowledge, this is the first stretchable synaptic transistor with oxide semiconductors, and it is also a major breakthrough in n-type stretchable synaptic transistors for high-speed and low-energy calculation and storage for brain-inspired computing.

Design and Implementation of Intelligent Robot Control System Integrating Computer Vision and Mechanical Engineering

With the rapid development of science and technology and industry, robot technology has become a key pillar in many fields, especially in industrial manufacturing, robots have been widely used in automated operations. However, in the face of the complex and changeable demands of modern industry, simple mechanized operation can no longer be satisfied, and intelligence has become the inevitable trend of robot technology development. By combining computer vision technology, this study provides robots with powerful environmental awareness and target recognition capabilities, thus achieving higher-level autonomous operation and decision-making. Aiming at the intelligent sorting system, this research adopts XYZ mechanical arm as the execution platform, equipped with TCS34725 color sensor to identify the color of articles, and integrates Hikvision industrial camera and NVIDIA Jetson TX2 image processor to capture and process image data, so as to achieve accurate positioning of articles. In the aspect of software design, this research realizes the function of accurately sorting different color items from the conveyor belt by combining color recognition algorithm and image processing technology with mechanical engineering control. The test results of the system show that the system has high accuracy and stability in color recognition and object positioning, and the trajectory accuracy of the manipulator meets the requirements, which verifies the realization of the research goal. The intelligent robot control system designed in this paper not only improves the level of industrial automation and reduces labor costs, but also broadens the application fields of robots in complex environments.

Efficient recognition of fish feeding behavior: A novel two-stage framework pioneering intelligent aquaculture strategies

In the domain of aquaculture, the act of feeding fish is a pivotal factor influencing both the growth of the fish and the associated cultivation costs. The implementation of intelligent feeding strategies is a crucial prerequisite for maintaining fish health and minimizing costs, with the accurate discernment of fish feeding behavior serving as the fundamental basis for the realization of such strategies. Addressing the issues of high data redundancy and substantial noise content inherent in the datasets utilized by existing identification models, as well as the intricate design and suboptimal execution efficiency of the model structures, this study introduces a two-stage framework for discriminating fish feeding behavior. In the initial stage, a re-parameterizable multi-scale object detection model is established, facilitating the acquisition of the spatial distribution of fish schools. This process effectively eliminates redundant data and noise, decouples the training and inference processes of the model, equivalently transforms the complex network training weights, and simplifies the inference process of the model. An analysis of the dataset characteristics is conducted, leading to the optimization of the model detector’s design and a reduction in both the model parameters and computational requirements. In the subsequent stage, responding to the key data characteristics of the spatial distribution of fish schools, a lightweight behavior recognition model is designed. This model enables the rapid and accurate identification of fish feeding behavior. A plethora of experimental results demonstrate that the proposed method can achieve a high recognition accuracy (Acc 83.33%) while operating under the constraints of minimal model parameters and computations (6.45M Params, 8.135G FLOPs). This provides a robust model foundation for the industrial application of the algorithm, underscoring the significant potential of the proposed method in advancing intelligent feeding strategies in aquaculture.

Speech emotion recognition based on bi-directional acoustic–articulatory conversion

Acoustic and articulatory signals are naturally coupled and complementary. The challenge of acquiring articulatory data and the nonlinear ill-posedness of acoustic–articulatory conversions have resulted in previous studies on speech emotion recognition (SER) primarily relying on unidirectional acoustic–articulatory conversions. However, these studies have ignored the potential benefits of bi-directional acoustic–articulatory conversion. Addressing the problem of nonlinear ill-posedness and effectively extracting and utilizing these two modal features in SER remain open research questions. To bridge this gap, this study proposes a Bi-A2CEmo framework that simultaneously addresses the bi-directional acoustic–articulatory conversion for SER. This framework comprises three components: a Bi-MGAN that addresses the nonlinear ill-posedness problem, KCLNet that enhances the emotional attributes of the mapped features, and ResTCN-FDA that fully exploits the emotional attributes of the features. Another challenge is the absence of a parallel acoustic–articulatory emotion database. To overcome this issue, this study utilizes electromagnetic articulography (EMA) to create a multi-modal acoustic–articulatory emotion database for Mandarin Chinese called STEM-E2VA. A comparative analysis is then conducted between the proposed method and state-of-the-art models to evaluate the effectiveness of the framework. Bi-A2CEmo achieves an accuracy of 89.04% in SER, which is an improvement of 5.27% compared with the actual acoustic and articulatory features recorded by the EMA. The results for the STEM-E2VA dataset show that Bi-MGAN achieves a higher accuracy in mapping and inversion than conventional conversion networks. Visualization of the mapped features before and after enhancement reveals that KCLNet reduces the intra-class spacing while increasing the inter-class spacing of the features. ResTCN-FDA demonstrates high recognition accuracy on three publicly available datasets. The experimental results show that the proposed bi-directional acoustic–articulatory conversion framework can significantly improve the SER performance.

High-Resolution Recognition of Orbital Angular Momentum Modes in Asymmetric Bessel Beams Assisted by Deep Learning

Abstract Fractional orbital angular momentum (OAM) vortex beams present a promising way to increase the data throughput in optical communication systems. Nevertheless, high-precision recognition of fractional OAM with different propagation distances remains a significant challenge. We develop a convolutional neural network (CNN) method to realize high-resolution recognition of OAM modalities, leveraging asymmetric Bessel beams imbued with fractional OAM. Experimental results prove that our method achieves a recognition accuracy exceeding 94.3% for OAM modes, with an interval of 0.05, and maintains a high recognition accuracy above 92% across varying propagation distances. The findings of our research will be poised to significantly contribute to the deployment of fractional OAM beams within the domain of optical communications.

Adaptive CAPTCHA: A CRNN-Based Text CAPTCHA Solver with Adaptive Fusion Filter Networks

Text-based CAPTCHAs remain the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs), are the mainstream approach for text CAPTCHA recognition and are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment; they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive CAPTCHA with a CNN combined with an RNN (CRNN) module and trainable Adaptive Fusion Filtering Networks (AFFN), which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexities show that, compared with the baseline model Deep CAPTCHA, the number of parameters of our proposed model is reduced by about 70%, and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed. Compared with several of the latest models, the model proposed by the study also has better comprehensive performance.

Method for Constructing Neural Network Means for Recognizing Scenes of Political Extremism in Graphic Materials of Online Social Networks

Countering the spread of calls for political extremism through graphic content on online social networks is becoming an increasingly pressing problem that requires the development of new technological solutions, since traditional approaches to countering are based on the results of recognizing destructive content only in text messages. Since in modern conditions neural network tools for analyzing graphic information are considered the most effective, it is assumed that it is advisable to use such tools for analyzing images and video materials in online social networks, taking into account the need to adapt them to the expected conditions of use, which are determined by the wide variability in the size of graphic content, the presence of typical interference, limited computing resources of recognition tools. Using this thesis, a method has been proposed that makes it possible to implement the construction of neural network recognition tools adapted to the specified conditions. For recognition, the author's neural network model was used, which, due to the reasonable determination of the architectural parameters of the low-resource convolutional neural network of the MobileNetV2 type and the recurrent neural network of the LSTM type, which makes up its structure, ensures high accuracy of recognition of scenes of political extremism both in static images and in video materials under limited computing conditions resources. A mechanism was used to adapt the input field of the neural network model to the variability of the size of graphic resources, which provides for scaling within acceptable limits of the input graphic resource and, if necessary, filling the input field with zeros. Levelling out typical noise is ensured by using advanced solutions in the method for correcting brightness, contrast and eliminating blur of local areas in images of online social networks. Neural network tools developed on the basis of the proposed method for recognizing scenes of political extremism in graphic materials of online social networks demonstrate recognition accuracy at the level of the most well-known neural network models, while ensuring a reduction in resource intensity by more than 10 times. This allows the use of less powerful equipment, increases the speed of content analysis, and also opens up prospects for the development of easily scalable recognition tools, which ultimately ensures an increase in security and a reduction in the spread of extremist content on online social networks. It is advisable to correlate the paths for further research with the introduction of the Attention mechanism into the neural network model used in the method, which will make it possible to increase the efficiency of neural network analysis of video materials.

Cloud maps highlighting dynamic characteristics of surface signal to improve time-varying wear evaluation accuracy

This paper proposes a high accuracy time-varying wear evolution method with cloud maps highlighting dynamic characteristics of surface signal. Firstly, the cloud map method is established by arrangement of measured data, thus time-varying wear evolution process is visualized on a series of plane figures for preliminary qualitative analysis. Then, high accuracy recognition of time-varying wear states is realized by cloud map shape parameters, including kurtosis and 1-D kernel density function highlighting distribution information of surface signal. The relative recognition degree by cloud map shape parameters are higher than those of friction coefficient, Root-Mean-Square (RMS) deviation and fractal dimension. Finally, high accuracy time-varying wear life prediction is realized by cloud map size growing speed highlighting waviness information of surface signal. The relative prediction error is reduced from more than 20% to less than 10% compared with friction coefficient and roughness.

Enhancing Signal Recognition Accuracy in Delay-Based Optical Reservoir Computing: A Comparative Analysis of Training Algorithms

To improve the accuracy of signal recognition in delay-based optical reservoir computing (RC) systems, this paper proposes the use of nonlinear algorithms at the output layer to replace traditional linear algorithms for training and testing datasets and apply them to the identification of frequency-modulated continuous wave (FMCW) LiDAR signals. This marks the inaugural use of the system for the identification of FMCW LiDAR signals. We elaborate on the fundamental principles of a delay-based optical RC system using an optical-injected distributed feedback laser (DFB) laser and discriminate four FMCW LiDAR signals through this setup. In the output layer, three distinct training algorithms—namely linear regression, support vector machine (SVM), and random forest—were employed to train the optical reservoir. Upon analyzing the experimental results, it was found that regardless of the size of the dataset, the recognition accuracy of the two nonlinear training algorithms was superior to that of the linear regression algorithm. Among the two nonlinear algorithms, the Random Forest algorithm had a higher recognition accuracy than SVM when the sample size was relatively small.