Neural Network-based Recognition Research Articles

Neural network-based recognition of multiple nanobubbles in graphene

We present a machine learning method for swiftly identifying nanobubbles in graphene, crucial for understanding electronic transport in graphene-based devices. Nanobubbles cause local strain, impacting graphene's transport properties. Traditional techniques like optical imaging are slow and limited for characterizing multiple nanobubbles. Our approach uses neural networks to analyze graphene's density of states, enabling rapid detection and characterization of nanobubbles from electronic transport data. This method swiftly enumerates nanobubbles and surpasses conventional imaging methods in efficiency and speed. It enhances quality assessment and optimization of graphene nanodevices, marking a significant advance in condensed matter physics and materials science. Our technique offers an efficient solution for probing the interplay between nanoscale features and electronic properties in two-dimensional materials.

Radar Emitter Signal Intra-Pulse Modulation Open Set Recognition Based on Deep Neural Network

Radar emitter signal intra-pulse modulation recognition is important for modern electronic reconnaissance systems to analyze target radar systems. In the actual environment, the intra-pulse modulations of the sampled radar emitter signals contain not only the known types in the library but also the unknown types. Therefore, the existing recognition methods, which are based on a closed set, cannot recognize the unknown samples. In order to solve this problem, in this paper, we proposed a method for radar emitter signal intra-pulse modulation open set recognition. The proposed method could classify the known modulations and identify the unknown modulation by using an original deep neural network-based recognition model trained on a closed set, estimating the signal-to-noise ratio, and calculating the reconstruction loss by an encoder–decoder model. For a given sample, the original deep neural network-based recognition model will label it as a certain known class temporarily. By estimating the SNR of the sample and calculating the reconstruction loss by inputting the sample to the corresponding encoder–decoder model related to the temporary predicted known class, whether the sample belongs to the predicted temporary known class or the unknown class will be confirmed. Experiments were conducted with five different openness conditions. The experimental results indicate that the proposed method has good performance on radar emitter signal intra-pulse modulation open set recognition.

Coherence modulation for anti-turbulence deep learning recognition of vortex beam

Acquiring topological charge in real-time for vortex beams encounters numerous challenges due to the turbulent atmosphere and coherence degradation. We propose an experimental scheme employing the strong detail extraction capability of deep neural networks to recognize the topological charge of partially coherent vortex beams propagating through the turbulent atmosphere and encountering unknown obstacles. Notably, coherence modulation has demonstrated advantages in deep neural network-based recognition. By comparing with high-coherence vortex beams, the deep neural network accurately recognizes topological charges for low-coherence vortex beams using only half of the available dataset. Furthermore, when the turbulent atmosphere and obstacles were considered, the accuracy of low-coherence vortex beams surpassed that of high-coherence vortex beams with equal amounts of training data. Additionally, the encrypted optical communication using partially coherent vortex beams was demonstrated. The coherence parameter significantly enhanced the channel capacity. This study holds potential for applications in free-space optical communication.

Convolutional neural network-based recognition method for volleyball movements

With the development of network technology and computer intelligent monitoring technology, a large number of video data came into being. In view of the analysis of specific targets in video, the traditional artificial analysis method can not meet the existing needs. In volleyball teaching in college physical education, because each student has different movements, intelligent processing of video data has become a key issue. Through collecting and sorting out the relevant research results on behavior recognition, it is found that in the research of deep learning, the algorithm structure applied in this paper is representative, and its strong learning ability, especially compared with the traditional algorithm, can more accurately identify human movements, natural language processing and so on, but the research on volleyball action recognition is still less. Therefore, this paper constructs a data set, improves the convolution neural network model, subsequently, new models are constructed through the neural network structure to improve the accuracy of the nonlinear expression and optimize the content of the input data. In order to more accurately analyze the effectiveness of this algorithm, the new data are obtained by grouping the volleyball games in college sports courses. Compared with the original paper, the accuracy of the improved 3D network is improved by 3.3%–88.5%, and the complexity is reduced by 33.6%.

Hand Anatomy and Neural Network-Based Recognition for Sign Language

This paper presents a model based on hand anatomy and neural network for the recognition of sign language. Feature extraction is done by using FAST and SIFT techniques. Out of these extracted features, only essential hand landmarks are selected using hand anatomy. NN is then used for the training and testing of the model. The proposed model is evaluated on sign language gestures used for medical purposes, general purposes, and family & relative purposes. The results prove that the proposed model has achieved fast and highly accurate results when compared with other available models. The model has achieved a recognizable accuracy of 99.85%, 97.55%, and 98.85%, on medical purposes, general purposes, and family & relative purposes, respectively.

Evaluation of the Quality of Practical Teaching of Agricultural Higher Vocational Courses Based on BP Neural Network

Agriculture is the backbone of any developing or developed country that makes any living to survive. To make food available throughout the year, it is necessary to know about agriculture and the work and strategies involved. Hence, agricultural courses have to be introduced to higher education students. Additionally, agriculture-related methods are available in many higher education institutions for longer. However, students and teachers will face difficulties in real-time practical classes during certain challenging circumstances. These situations require the teacher to utilize trending technologies to improve the teaching and learning process and to make it more manageable. In this study, for this process, a novel neural network-based recognition algorithm (NN-RA) is implemented that works similarly to a backpropagation neural network (BP-NN) to provide a practical agriculture course. The proposed BP-NN is compared with the existing NN-RA, I-SC, and I-VDT algorithms based on the data transfer and signal-to-noise ratio. From the results, it can be observed that the proposed BP-NN attains a higher accuracy in data transfer of 99%.

Neural Network-based Recognition and Virtual Simulation Algorithms, Interactive 3D Geo-Visualization and Neuromorphic Computing Systems, and Tactile Sensing and Cognitive Modeling Technologies in Web3-powered Metaverse Worlds

Neural Network-based Recognition and Virtual Simulation Algorithms, Interactive 3D Geo-Visualization and Neuromorphic Computing Systems, and Tactile Sensing and Cognitive Modeling Technologies in Web3-powered Metaverse Worlds

Machine learning models can predict the presence of variants in hemoglobin: artificial neural network-based recognition of human hemoglobin variants by HPLC

Abstract Objectives This article presents the use of machine learning techniques such as artificial neural networks, K-nearest neighbors (KNN), naive Bayes, and decision trees in the prediction of hemoglobin variants. To the best of our knowledge, this is the first study using machine learning models to predict suspicious cases with HbS or HbD Los Angeles carriers state. Methods We had a dataset of 238 observations, of which 128 were HbD carriers, and 110 were HbS carriers. The features were age, sex, RBC, Hb, HTC, MCV, MCH, RDW, serum iron, TIBC, ferritin, HbA2, HbF, HbA0, retention time (RT) of the abnormal peak, and the area under the peak of the abnormal peak. KNN, naive Bayes, decision tree models, and artificial neural network models were trained. Model performances were estimated using 7-fold cross-validation. Results When RT, the key point of differentiation used in high-performance liquid chromatography (HPLC), was included as a feature, all models performed well. When RT was excluded (eliminated), the deep learning model performed the best (Accuracy: 0.99; Specificity: 0.99; Sensitivity: 0.99; F1 score: 0.99), while the naive Bayes model performed the worst (Accuracy: 0.94; Specificity: 0.97; Sensitivity: 0.90; F1 score: 0.93). Conclusions Deep learning and decision tree models have demonstrated high performance and have the potential to be integrated into medical laboratory work practices as a tool for hemoglobinopathy detection. These outcomes suggest that when machine learning models are fed enough data, they can detect a wide range of hemoglobin variants. However, more comprehensive studies with data from a larger number of patients and hemoglobinopathies will be useful for validating our models.

A Convolutional Neural Network-Based Recognition Method of Gear Performance Degradation Mode

Abstract In an increasingly intelligent modern society, whether in industrial production activities or daily life, mechanical transmission equipment is more and more widely used. Once a failure occurs, it will not only cause the stagnation of industrial production, bring huge economic losses and environmental pollution, but may also cause casualties. Therefore, it is particularly important to identify and monitor the performance degradation of mechanical equipment. Based on the convolutional neural network (CNN), a stacking incremental deformable residual block network recognition model is proposed. This method converts the one-dimensional signal recognition problem into an image recognition problem. The average pooling layer replaces the fully connected layer, and the large-size convolution kernel is replaced with a small-size convolution kernel. With the recognition of the gear performance degradation modes, the experiment proves that the multi-channel recognition model has a better recognition effect.

Selected Energy Consumption Aspects of Sensor Data Transmission in Distributed Multi-Microcontroller Embedded Systems

Wireless network devices are currently a hot topic in research related to human health, control systems, smart homes, and the Internet of Things (IoT). In the shadow of the coronavirus pandemic, they have gained even more attention. This remote and contactless distributed sensing technology enabled monitoring of vital signs in real-time. Many of the devices are battery powered, so appropriate management of available energy is crucial for lengthening autonomous operation time without affecting weight, size, maintenance requirement, and user acceptance. In this paper, we discuss energy consumption aspects of sensor data transmission using wireless Bluetooth Low Energy Mesh Long Range (BLE-M-LR) technology. Papers in the field of energy savings in wireless networks do not directly address the problem of the dependence of the energy needed for transmission on the type and degree of data preprocessing, which is the novelty and uniqueness of this work. We built and studied a prototype system designed to work as a multimodal sensing node in a compound IoT application targeted to assisted living. To analyze multiple energy-related aspects, we tested it in various operation and data transmission modes: continuous, periodic, and event-based. We also implemented and tested two alternative sensor-side processing procedures: deterministic data stream reduction and neural network-based recognition and labeling of the states. Our results reveal that event-based or periodic operation allows the node for years-long operating, and the sensor-side processing may degrade the power economy more than it benefits from savings made on transmission of concise data.

Eye Movement Prediction Based on Adaptive BP Neural Network

This paper uses adaptive BP neural networks to conduct an in-depth examination of eye movements during reading and to predict reading effects. An important component for the implementation of visual tracking systems is the correct detection of eye movement using the actual data or real-world datasets. We propose the identification of three typical types of eye movements, namely, gaze, leap, and smooth navigation, using an adaptive BP neural network-based recognition algorithm for eye movement. This study assesses the BP neural network algorithm using the eye movement tracking sensors. For the experimental environment, four types of eye movement signals were acquired from 10 subjects to perform preliminary processing of the acquired signals. The experimental results demonstrate that the recognition rate of the algorithm provided in this paper can reach up to 97%, which is superior to the commonly used CNN algorithm.

A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition

We present a saliency-based patch sampling strategy for recognizing artistic media from artwork images using a deep media recognition model, which is composed of several deep convolutional neural network-based recognition modules. The decisions from the individual modules are merged into the final decision of the model. To sample a suitable patch for the input of the module, we devise a strategy that samples patches with high probabilities of containing distinctive media stroke patterns for artistic media without distortion, as media stroke patterns are key for media recognition. We design this strategy by collecting human-selected ground truth patches and analyzing the distribution of the saliency values of the patches. From this analysis, we build a strategy that samples patches that have a high probability of containing media stroke patterns. We prove that our strategy shows best performance among the existing patch sampling strategies and that our strategy shows a consistent recognition and confusion pattern with the existing strategies.

Analysis of Stadium Operation Risk Warning Model Based on Deep Confidence Neural Network Algorithm.

In this paper, a deep confidence neural network algorithm is used to design and deeply analyze the risk warning model for stadium operation. Many factors, such as video shooting angle, background brightness, diversity of features, and the relationship between human behaviors, make feature attribute-based behavior detection a focus of researchers' attention. To address these factors, researchers have proposed a method to extract human behavior skeleton and optical flow feature information from videos. The key of the deep confidence neural network-based recognition method is the extraction of the human skeleton, which extracts the skeleton sequence of human behavior from a surveillance video, where each frame of the skeleton contains 18 joints of the human skeleton and the confidence value estimated for each frame of the skeleton, and builds a deep confidence neural network model to classify the dangerous behavior based on the obtained skeleton feature information combined with the time vector in the skeleton sequence and determine the danger level of the behavior by setting the corresponding threshold value. The deep confidence neural network uses different feature information compared with the spatiotemporal graph convolutional network. The deep confidence neural network establishes the deep confidence neural network model based on the human optical flow information, combined with the temporal relational inference of video frames. The key of the temporal relationship network-based recognition method is to extract some frames from the video in an orderly or random way into the temporal relationship network. In this paper, we use several methods for comparison experiments, and the results show that the recognition method based on skeleton and optical flow features is significantly better than the algorithm of manual feature extraction.

Deep neural network-based recognition of entities in Chinese online medical inquiry texts

It is quite challenging to correctly identify entities such as disease names, symptoms, and drugs from Chinese online medical inquiry texts. On the one hand, traditional natural language related methods cannot be directly applied to the field of online medical inquiry. Although supervised or unsupervised learning algorithms provide an entity recognition strategy for medical inquiries on online platforms, these methods either rely extensively on specific knowledge sources or artificially-designed features, or have a strong self-adaptivity, can barely obtain fairly good entity recognition outcomes, and consequently have weak generalization. On the other hand, Chinese online medical inquiry data is characterized by a large volume and excessively rich unstructured data, medical entities are indeed distributed in a sparse way, and the Chinese characters and words are quite complicated. It is difficult to establish a robust model for the recognition of entities in Chinese online medical inquiry texts. Therefore, establishing a new deep neural network (OMINer-CE) is the attempt of this paper. First, in order to form a proper feature strategy, the basic features of other tasks are introduced, while extended features, such as continuous bag of word cluster (CBOWC) feature, are constructed. Second, the feature vectors of Chinese character and word fusion are introduced to reserve all the Chinese character information of original sequences while introducing Chinese word-based semantic information. Third, a context encoding layer and a label decoding layer are introduced; On the basis of the recurrent neural network model BiLSTM, a convolutional neural network (CNN) is added to learn more key local features of Chinese word context, and the attention mechanism is used to obtain the long-distance dependency of the Chinese words to form a OMINer model. Finally, the basic and extended feature vectors are integrated into the OMINer model, and the grammatical and semantic information contained in the labeled texts is obtained from different perspectives. Therefore, it considers the feature strategies of Chinese online medical platforms, and realizes a strong self-adaptivity by utilizing the deep neural network. It is showed by the experiments that preferably good performances can be realized by combining the CE basic and extended feature vectors in the BiLSTM of the OMINer model, suggesting that the OMINer-CE model improves the performance of recognizing entities in Chinese online medical inquiry texts.

A Survey on Artificial Intelligence in Chinese Sign Language Recognition

Chinese Sign Language (CSL) offers the main means of communication for the hearing impaired in China. Sign Language Recognition (SLR) can shorten the distance between the hearing-impaired and healthy people and help them integrate into the society. Therefore, SLR has become the focus of sign language application research. Over the years, the continuous development of new technologies provides a source and motivation for SLR. This paper aims to cover the most recent approaches in Chinese Sign Language Recognition (CSLR). With a thorough review of superior methods from 2000 to 2019 in CSLR researches, various techniques and algorithms such as scale-invariant feature transform, histogram of oriented gradients, wavelet entropy, Hu moment invariant, Fourier descriptor, gray-level co-occurrence matrix, dynamic time warping, principal component analysis, autoencoder, hidden Markov model (HMM), support vector machine (SVM), random forest, skin color modeling method, k-NN, artificial neural network, convolutional neural network (CNN), and transfer learning are discussed in detail, which are based on several major stages, that is, data acquisition, preprocessing, feature extraction, and classification. CSLR was summarized from some aspect as follows: methods of classification and feature extraction, accuracy/performance evaluation, and sample size/datasets. The advantages and limitations of different CSLR approaches were compared. It was found that data acquisition is mainly through Kinect and camera, and the feature extraction focuses on hand’s shape and spatiotemporal factors, but ignoring facial expressions. HMM and SVM are used most in the classification. CNN is becoming more and more popular, and a deep neural network-based recognition approach will be the future trend. However, due to the complexity of the contemporary Chinese language, CSLR generally has a lower accuracy than other SLR. It is necessary to establish an appropriate dataset to conduct comparable experiments. The issue of decreasing accuracy as the dataset increases needs to resolve. Overall, our study is hoped to give a comprehensive presentation for those people who are interested in CSLR and SLR and to further contribute to the future research.

Road structure classification through artificial neural network for automotive radar systems

This study proposes an artificial neural network-based method to classify road structures for automotive radar systems. Generally, road structures generate unwanted echoes called clutter, which degrades the performance of target detection, and may cause critical errors in autonomous driving modes. However, recognition and classification of each individual structure type is very difficult, because there are various types of structures made by different materials which cause ambiguity in the recognition and classification process. To deal with these classification ambiguities, the authors propose an artificial neural network-based recognition and classification method. Road structures are classified by applying artificial neural network to the frequency domain-received signals of automotive radar systems. Once the neural network has been trained with the received signals, it is used to determine the type of road structure with instantaneous received signals. The classification performance was evaluated by experimenting with the number of antenna elements and radar snapshots. In addition, to find the most suitable artificial neural network structure, the authors experimented with the number of nodes and layers. After completing a period of deep learning using actual experimental data, the total classification accuracy was about 95%.

Stereo- and neural network-based pedestrian detection

Pedestrian detection is essential to avoid dangerous traffic situations. We present a fast and robust algorithm for detecting pedestrians in a cluttered scene from a pair of moving cameras. This is achieved through stereo-based segmentation and neural network-based recognition. The algorithm includes three steps. First, we segment the image into sub-image object candidates using disparities discontinuity. Second, we merge and split the sub-image object candidates into sub-images that satisfy pedestrian size and shape constraints. Third, we use intensity gradients of the candidate sub-images as input to a trained neural network for pedestrian recognition. The experiments on a large number of urban street scenes demonstrate that the proposed algorithm: (1) can detect pedestrians in various poses, shapes, sizes, clothing, and occlusion status; (2) runs in real-time; and (3) is robust to illumination and background changes.

Distance features for neural network-based recognition of handwritten characters

Features play an important role in OCR systems. In this paper, we propose two new features which are based on distance information. In the first feature (called DT, Distance Transformation), each white pixel has a distance value to the nearest black pixel. The second feature is called DDD (Directional Distance Distribution) which contains rich information encoding both the black/white and directional distance distributions. A new concept of map tiling is introduced and applied to the DDD feature to improve its discriminative power. For an objective evaluation and comparison of the proposed and conventional features, three distinct sets of characters (i.e., numerals, English capital letters, and Hangul initial sounds) have been tested using standard databases. Based on the results, three propositions can be derived to confirm the superiority of both the DDD feature and the map tilings.