Neural Network Recognition Algorithm Research Articles

Real-Time Recognition and Localization of Apples for Robotic Picking Based on Structural Light and Deep Learning

The apple is a delicious fruit with high nutritional value that is widely grown around the world. Apples are traditionally picked by hand, which is very inefficient. The development of advanced fruit-picking robots has great potential to replace manual labor. A major prerequisite for a robot to successfully pick fruits the accurate identification and positioning of the target fruit. The active laser vision systems based on structured algorithms can achieve higher recognition rates by quickly capturing the three-dimensional information of objects. This study proposes to combine the laser active vision system with the YOLOv5 neural network model to recognize and locate apples on trees. The method obtained accurate two-dimensional pixel coordinates, which, when combined with the active laser vision system, can be converted into three-dimensional world coordinates for apple recognition and positioning. On this basis, we built a picking robot platform equipped with this visual recognition system, and carried out a robot picking experiment. The experimental findings showcase the efficacy of the neural network recognition algorithm proposed in this study, which achieves a precision rate of 94%, an average precision mAP% of 92.86%, and a spatial localization accuracy of approximately 4 mm for the visual system. The implementation of this control method in simulated harvesting operations shows the promise of more precise and successful fruit positioning. In summary, the integration of the YOLOv5 neural network model with an active laser vision system presents a novel and effective approach for the accurate identification and positioning of apples. The achieved precision and spatial accuracy indicate the potential for enhanced fruit-harvesting operations, marking a significant step towards the automation of fruit-picking processes.

Algorithm for Recognition of Small Air Targets by Trajectory Features in Passive Bistatic Radar

Introduction. In the past few years, the rapid development and widespread use of unmanned aerial vehicles (UAVs) for solving a variety of tasks has created new threats. The problem of ensuring the safety of protected objects, especially in the area of critically important objects or in places with difficult ornithological conditions (airports, wind power facilities), is of particular importance. In this regard, the issue of detecting small air targets and recognizing their type and degree of danger is acquiring greater importance. This paper presents an algorithm for recognizing air targets based onartificial intelligence technology. The results of a comparative analysis of decision-making methods for recognizing small UAVs and birds based on their trajectory features are presented. The results obtained can be used in the development of systems for recognizing classes of small airborne targets in existing and future radar stations. Aim. Development of an algorithm for recognizing small air targets by trajectory features based on machine learning. Implementation and evaluation of the quality of decision-making methods in a given recognition problem. Materials and methods. Experimental data on the trajectories of UAVs and birds obtained in a passive bistatic radar system are used. The trajectory parameters of the targets and their statistical characteristics are calculated; a set of features for recognition is formed. Using the MATLAB software package, a program for implementing the recognition algorithm and analyzing the quality of decision-making methods was developed. Results. An algorithm for recognizing air targets based on artificial intelligence technology is presented. A comparative analysis of the six most common recognition methods based on machine learning (Naïve Bayes, decision trees, k-nearest neighbors, neural network recognition algorithm, support vector machine, random forests) was carried out, which showed that, under the conditions of this problem, the most effective are k-nearest neighbor method and support vector machine. Conclusion. The presented methods can be used to directly determine the class of targets from a set of marks of their trajectories. Further research will be aimed at developing and implementing a real-time recognition algorithm.

Advancing Bridge Construction Monitoring: AI-Based Building Information Modeling for Intelligent Structural Damage Recognition

ABSTRACT Building Information Modeling (BIM) has emerged as a transformative technology in the construction industry, revolutionizing various aspects of the field. The integration of Artificial Intelligence (AI) techniques with BIM holds significant promise and is gaining momentum in interdisciplinary applications. In China, the construction industry has witnessed notable advancements through the convergence of BIM, AI, and cloud data. However, the current state of intelligent construction technology in China reveals certain limitations that hinder its comprehensive development. This study addresses these challenges by focusing on the design of intelligent recognition algorithms for monitoring structural damage during bridge construction. Previous research has primarily employed classical neural network algorithms, but these approaches have exhibited certain limitations. This paper proposes innovative improvement measures to overcome these limitations and demonstrates their effectiveness through practical arithmetic examples. Furthermore, to enhance the intelligence level of the BIM system, this study integrates the improved neural network recognition algorithm into the BIM framework. The integration enables the BIM system to recognize and assess bridge structure damage efficiently and accurately. The outcomes of this research provide valuable insights into advancing the field of intelligent construction technology, particularly in the context of bridge construction monitoring.

Application of image recognition based on neural network algorithm in multimedia dance teaching

Neural network recognition algorithm is a deep learning-based convolutional neural network, which has been applied to target detection, image recognition, sound recognition and other fields. Although the recognition technology of convolutional neural network has been gradually stabilized, it is mainly implemented in single-machine serial mode. Therefore, there will be problems such as too long training time and insufficient memory capacity. According to the previous work, this paper has carried out related research and obtained some useful results. This paper focuses on the introduction of image recognition technology based on neural network algorithm. At the same time, this paper proposes a fast real-time image recognition algorithm, which has high recognition accuracy. In this paper, the existing algorithms mentioned in the paper are analyzed, the characteristics and shortcomings of all algorithms are summarized, and the appropriate combination of algorithms is selected for specific problems. On this basis, the acceleration method of artificial neural network is used to improve the algorithm of convolutional neural network image recognition technology. With the continuous development of education and the increase of the number of students year by year, the effect of classroom teaching becomes particularly important. Therefore, modern information technology is used to transfer the classroom teaching mode to the network and realize a new method of online remote online dance teaching. According to the actual situation of dance teaching, the advantages of multimedia dance teaching are analyzed. The software of multimedia dance teaching system is tested comprehensively, from the aspects of computer system memory occupancy rate and temperature, to test whether the activities of B/S mode multimedia dance teaching system meet the expected goals and requirements of each core module of multimedia dance teaching system.

Defect inspection of optical components based on dark-field polarization imaging and convolutional neural network recognition algorithms

Defect inspection of optical components based on dark-field polarization imaging and convolutional neural network recognition algorithms

Reconstruction of physical dance teaching content and movement recognition based on a machine learning model

With the technological development of movement recognition based on machine learning model algorithms, the content and movements for physical dance teaching are also seeking changes and innovations. In this paper, a set of three-dimensional convolutional neural network recognition algorithms based on a machine learning model is constructed through the collection to recognition of sports dance movement data. By collecting the skeleton information of typical movements of physical dance, a typical movement dataset of physical dance is constructed, which is recognized by the improved 3D convolutional neural network recognition algorithm under the machine learning model, and the method is validated on the public dataset. The experimental results show that the 3D CNNs in this paper can produce relatively satisfactory results for sports dance action recognition with high accuracy of action recognition, which verifies the feasibility of the 3D convolutional neural network action recognition algorithm under the machine learning model for the acquisition to recognition of sports dance actions. It illustrates that the future can be better to open a new direction of physical dance education content through machine learning models in this form.

Automatic Modulation Recognition Based on a DCN-BiLSTM Network.

Automatic modulation recognition (AMR) is a significant technology in noncooperative wireless communication systems. This paper proposes a deep complex network that cascades the bidirectional long short-term memory network (DCN-BiLSTM) for AMR. In view of the fact that the convolution operation of the traditional convolutional neural network (CNN) loses the partial phase information of the modulated signal, resulting in low recognition accuracy, we first apply a deep complex network (DCN) to extract the features of the modulated signal containing phase and amplitude information. Then, we cascade bidirectional long short-term memory (BiLSTM) layers to build a bidirectional long short-term memory model according to the extracted features. The BiLSTM layers can extract the contextual information of signals well and address the long-term dependence problems. Next, we feed the features into a fully connected layer. Finally, a softmax classifier is used to perform classification. Simulation experiments show that the performance of our proposed algorithm is better than that of other neural network recognition algorithms. When the signal-to-noise ratio (SNR) exceeds 4 dB, our model’s recognition rate for the 11 modulation signals can reach 90%.

A hydrate blockage recognition technique for natural gas pipelines based on BP neural network

In energy industry field, hydrate blockage in natural gas pipelines has become a critical issue with an increasing demand of natural gas in the world. In this paper, a hydrate blockage recognition technique has been proposed based on BP neural network, which can recognize leakage in natural gas pipelines as well. A monitoring system has been built for trials, which mainly includes a loudspeaker and a microphone for acoustic signals transmission and reception. This paper mainly introduces wavelet packet theory and BP neural network recognition algorithm for signal analysis and recognition purpose. The reflected signals are analyzed and extracted eigenvectors by using wavelet packet transform, then a three-layer BP neural network is built and trained. Experimental results show that this technique can recognize hydrate blockage and leakage effectively.

BP neural network recognition algorithm for scour monitoring of subsea pipelines based on active thermometry

Scour monitoring is an important concern for subsea pipeline systems. The active-thermometry-based scour monitoring is based on the difference of heat transfer properties between sediment and sand, recognizes the surrounding media though temperature changing patterns during heating and cooling processes, and hence detects the free spans. Based on the scour monitoring system, a two-layer BP neural network was employed to process the monitoring data and achieved media recognition. The network's inputs were normalized temperature time histories. The network's outputs denoted different media: sediment and water. To validate the method, three experiments were conducted; one was used for training the network and the other two for testing. Also, the effect of noise on the network's performance was studied through simulation. The results demonstrated the feasibility and robustness of the neural network.

The Research of Judging the Phenomenon of Roof Separation Based on Principle of Dynamic Time Warping Algorithm

Applying Wall tapping and roof sounding for coal blasting mining, excavation face to determine whether the status of roadway roof separation occurs. Firstly through beating the different parts of rock layers and record the received voice signal, which do the DTW feature extraction of the voice signal. Secondly based on the model database of constructed roof separated layer, determining the state of the roof combining with BP neural network recognition algorithm, after the extraction of DTW feature and the sequence data generated. Finally simulation and experiments show that identification method based on DTW, determining the state of the roof characteristic. Whether the roof separation of roadway occurs, to avoid the misjudgment problems of lack of experience in practical works.

About neural-network algorithms application in viseme classification problem with face video in audiovisual speech recognition systems

The paper considers the phoneme recognition by facial expressions of a speaker in voice-activated control systems. We have developed a neural network recognition algorithm by using the phonetic words decoding method and the requirement for isolated syllable pronunciation of voice commands. The paper presents the experimental results of viseme (facial and lip position corresponding to a particular phoneme) classification of Russian vowels. We show the dependence of the classification accuracy on the used classifier (multilayer feed-forward network, support vector machine, k-nearest neighbor method), image features (histogram of oriented gradients, eigenvectors, SURF local descriptors) and the type of camera (built-in or Kinect one). The best accuracy of speaker-dependent recognition is shown to be 85% for a built-in camera and 96% for Kinect depth maps when the classification is performed with the histogram of oriented gradients and the support vector machine.

Recognition of Individual Holstein Cattle by Imaging Body Patterns

A computer vision system was designed and validated to recognize an individual Holstein cattle by processing images of their body patterns. This system involves image capture, image pre-processing, algorithm processing, and an artificial neura ln etwork recognition algorithm. Optimum management of individuals is one of the most important factors in keeping cattle healthy and productive. In this study, an image-processing system was used to recognize individual Holstein cattle by identifying the body-pattern images captured by a charge-coupled device (CCD). A recognition system was developed and applied to acquire images of 49 cattles. The pixel values of the body images were transformed into input data comprising binary signals for the neural network. Images of the 49 cattle were analyzed to learn input layer elements, and ten cattles were used to verify the output layer elements in the neural network by using an individual recognition program. The system proved to be reliable for the individual recognition of cattles in natural light. (Asian-Aust. J. Anim. Sci. 2005. Vol 18, No. 8: 1194-1198)

Systematic study of pretransitional orientational order at the free surface of nCB liquid crystals (n=5-12) in the isotropic phase

A high precision rotating ellipsometer was used to perform a systematic study of the pretransitional orientational order induced by the free surface of n-alkylcyanobiphenyl liquid crystals (n=5-12) in the isotropic phase. All the compounds of this series show a complete wetting behaviour at the free surface. The temperature dependence of the surface order parameter was determined via calculations based on the Landau-de Gennes theory and the results show an even-odd behaviour. Moreover, we used a neural network recognition algorithm to reconstruct the order parameter profile S (z) near the surface. The results of this model-independent analysis are compared with the model based calculations.