Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Train pattern recognition.
Статті в журналах з теми "Train pattern recognition"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Train pattern recognition".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Ahmadian, Kushan, and Marina Gavrilova. "Chaotic Neural Network for Biometric Pattern Recognition." Advances in Artificial Intelligence 2012 (August 30, 2012): 1–9. http://dx.doi.org/10.1155/2012/124176.
Повний текст джерелаАнотація:
Biometric pattern recognition emerged as one of the predominant research directions in modern security systems. It plays a crucial role in authentication of both real-world and virtual reality entities to allow system to make an informed decision on granting access privileges or providing specialized services. The major issues tackled by the researchers are arising from the ever-growing demands on precision and performance of security systems and at the same time increasing complexity of data and/or behavioral patterns to be recognized. In this paper, we propose to deal with both issues by introducing the new approach to biometric pattern recognition, based on chaotic neural network (CNN). The proposed method allows learning the complex data patterns easily while concentrating on the most important for correct authentication features and employs a unique method to train different classifiers based on each feature set. The aggregation result depicts the final decision over the recognized identity. In order to train accurate set of classifiers, the subspace clustering method has been used to overcome the problem of high dimensionality of the feature space. The experimental results show the superior performance of the proposed method.
2
Wang, Yi, and Wei Lian Qu. "Multi-Axle Moving Train Loads Identification by Using Fuzzy Pattern Recognition Technique." Applied Mechanics and Materials 29-32 (August 2010): 1307–12. http://dx.doi.org/10.4028/www.scientific.net/amm.29-32.1307.
Повний текст джерелаАнотація:
Identification of multi-axle moving loads on bridge is very important for bridge design, construction, and maintenance in engineering field. It is complicated and time consuming to identify the multi-axle moving train loads with general identification methods and far away from practical practice. Based on the theory of fuzzy pattern recognition, the fuzzy pattern recognition method for multi-axle moving train loads identification on bridge is presented in this paper. The multi-axle moving loads pattern library on a simply supported bridge is established with numerical methods. Effect of measurement noise on the proposed method is investigated in three situations. The results show that the proposed identification method has a certain resistance to measurement noise and can realize moving train loads identification with high accuracy.
3
Joshila Grace, L. K., K. Rahul, and P. S. Sidharth. "An Efficient Action Detection Model Using Deep Belief Networks." Journal of Computational and Theoretical Nanoscience 16, no. 8 (August 1, 2019): 3232–36. http://dx.doi.org/10.1166/jctn.2019.8168.
Повний текст джерелаАнотація:
Computer Vision and image processing have gained an enormous advance in the field of machine learning techniques. Some of the major research areas within machine learning are Action detection and Pattern Recognition. Action recognition is a new advancement of pattern recognition approaches where the actions performed by any action or living being is tracked and monitored. Action recognition still encounters some challenges that needs to be looked upon and perform recognize the actions is a very minimal time. Networks like SVM and Neural Networks are used to train the network in such a way they are able to detect a pattern of an action when a new frame is given. In this paper, we have proposed a model which detects patterns of actions from a video or an image. Bounding boxes are used to detect the actions and localize it. Deep Belief Network is used to train the model where numerous images having actions are given as the training set. The performance evaluation was done on the model and it is observed that it detects the actions very accurately when a new image is given to the network.
4
Li, Lu, Guo Qing Jiang, Tian Ye Niu, Yi Wang, Yong Lu, Qi Lan, Li Chang, Ya Lin Liu, and Chao Chen. "High Voltage Equipment PD Pattern Recognition Based on BP Classifier." Applied Mechanics and Materials 734 (February 2015): 99–103. http://dx.doi.org/10.4028/www.scientific.net/amm.734.99.
Повний текст джерелаАнотація:
The corresponding discharge waveforms were detected by ultrasonic sensor. The dimension of feature vectors extracted from discharge waveforms were reduced by local linear embedding algorithm. The processed vectors were used as input to train and test BP_Adaboost classifier. Recognition results show that, high voltage reactor insulating defects recognition with this method can reduce the calculation and maintain a high recognition rate at the same time. This shows its effectiveness in the application of partial discharge pattern recognition.
5
Manzi, Daniel, Bruno Brentan, Gustavo Meirelles, Joaquín Izquierdo, and Edevar Luvizotto. "Pattern Recognition and Clustering of Transient Pressure Signals for Burst Location." Water 11, no. 11 (October 30, 2019): 2279. http://dx.doi.org/10.3390/w11112279.
Повний текст джерелаАнотація:
A large volume of the water produced for public supply is lost in the systems between sources and consumers. An important—in many cases the greatest—fraction of these losses are physical losses, mainly related to leaks and bursts in pipes and in consumer connections. Fast detection and location of bursts plays an important role in the design of operation strategies for water loss control, since this helps reduce the volume lost from the instant the event occurs until its effective repair (run time). The transient pressure signals caused by bursts contain important information about their location and magnitude, and stamp on any of these events a specific "hydraulic signature". The present work proposes and evaluates three methods to disaggregate transient signals, which are used afterwards to train artificial neural networks (ANNs) to identify burst locations and calculate the leaked flow. In addition, a clustering process is also used to group similar signals, and then train specific ANNs for each group, thus improving both the computational efficiency and the location accuracy. The proposed methods are applied to two real distribution networks, and the results show good accuracy in burst location and characterization.
6
Yuan, Jiaxin, and Zhe Kan. "Research and Implementation of Flow Pattern Recognition for Gas-liquid Two-phase Flows Based on GoogLeNet." Journal of Physics: Conference Series 2224, no. 1 (April 1, 2022): 012021. http://dx.doi.org/10.1088/1742-6596/2224/1/012021.
Повний текст джерелаАнотація:
Abstract In order to solve the flow pattern recognition problem of gas-liquid two-phase flow in pipelines, this paper uses high-speed photography to sample the flow patterns of transparent pipe sections and combines the GoogLeNet convolutional neural network model under migration learning to implement a flow pattern recognition method with small samples. In this paper, the GoogLeNet Inception V1 network is used, and the convolutional layer and the pooling layer weights parameters obtained from its training on the imageNet dataset are retained, and the flow pattern samples obtained on the gas-liquid two-phase flow experimental platform are used to train the network model. The recognition accuracy was 98.37% with a training set of 400 and a test set of 100 samples of each flow type. The convolutional neural network directly uses images as data input without operations such as image pre-processing and feature extraction, and its unique fine-grained feature extraction enables the recognition of images by convolutional neural networks at a nearly human level.
7
Cerreto, Fabrizio, Bo Friis Nielsen, Otto Anker Nielsen, and Steven S. Harrod. "Application of Data Clustering to Railway Delay Pattern Recognition." Journal of Advanced Transportation 2018 (2018): 1–18. http://dx.doi.org/10.1155/2018/6164534.
Повний текст джерелаАнотація:
K-means clustering is employed to identify recurrent delay patterns on a high traffic railway line north of Copenhagen, Denmark. The clusters identify behavioral patterns in the very large (“big data”) datasets generated automatically and continuously by the railway signal system. The results reveal the conditions where corrective actions are necessary, showing the cases where recurrent delay patterns take place. Delay profiles and delay change profiles are generated from timestamps to compare different train runs and to partition the set of observations into groups of similar elements. K-means clustering can identify and discriminate different patterns affecting the same stations, which is otherwise difficult in previous approaches based on visual inspection. Classical methods of univariate analysis do not reveal these patterns. The demonstrated methodology is scalable and can be applied to any system of transport.
8
Hu, Ke Dong, Yi Xuan Ji, and Da Peng Tan. "Pattern Recognition of the Soft Abrasive Flow Based on Wavelet Packet." Advanced Materials Research 588-589 (November 2012): 756–60. http://dx.doi.org/10.4028/www.scientific.net/amr.588-589.756.
Повний текст джерелаАнотація:
A Pattern Recognition method based on wavelet packet and artificial neural is proposed for solid-liquid two-phase flow characteristic parameters and the non-linear relationship between flow pattern. This method firstly established the physical and dynamic model, then set a monitoring point. To get the optimum wavelet tree and its information entropy, six floors of wavelet packet was used to decompose the collected velocity fluctuation signal. Transported the proper vector which is component by information entropy into Back Propagation neural network to train and identify. The recognition results show that this method can effectively overcome the subjectivity of traditional identification methods. It has good recognition effect, thus provide an effective choice for solid-liquid two-phase flow pattern recognition.
9
Adeyemi, Oladimeji, Martins Irhebhude, and Adeola Kolawole. "Speed Breakers, Road Marking Detection and Recognition Using Image Processing Techniques." Advances in Image and Video Processing 7, no. 5 (November 8, 2019): 30–42. http://dx.doi.org/10.14738/aivp.75.7205.
Повний текст джерелаАнотація:
This paper presents a image processing technique for speed breaker, road marking detection and recognition. An Optical Character Recognition (OCR) algorithm was used to recognize traffic signs such as “STOP” markings and a Hough transform was used to detect line markings which serves as a pre-processing stage to determine when the proposed technique does OCR or speed breaker recognition. The stopline inclusion serves as a pre-processing stage that tells the system when to perform stop marking recognition or speed breaker recognition. Image processing techniques was used for the processing of features from the images. Local Binary Pattern (LBP) was extracted as features and employed to train the Support Vector Machine (SVM) classifier for speed breaker recognition. Experimental results shows 79%, 100% “STOP” sign and speed breaker recognitions respectively. The proposed system goes very well for the roads which are constructed with proper painting irrespective of their dimension.
10
Fang, Huijuan, Yongji Wang, Jiping He, and Shan Liu. "Temporal pattern recognition using spiking neural networks for cortical neuronal spike train decoding." IFAC Proceedings Volumes 41, no. 2 (2008): 5203–8. http://dx.doi.org/10.3182/20080706-5-kr-1001.00874.
Повний текст джерела
11
Wang, Xin, and He Pan. "Study of Face Feature Extraction and Recognition Techniques Based on Wavelet Analysis." Advanced Materials Research 1030-1032 (September 2014): 1810–13. http://dx.doi.org/10.4028/www.scientific.net/amr.1030-1032.1810.
Повний текст джерелаАнотація:
Face recognition is a research hotspot of pattern recognition and artificial intelligence. This paper presents a method of extract face feature based on Wavelet. First, reduce vector dimension by wavelet decomposition of the image, second, train the multi class support vector machine (SVM) model by face feature vector extracted and make face recognition finally. The experiments on ORL face image database of the algorithm shows the superiority of the proposed algorithm in terms of recognition performance.
12
Wu, Yi-Da, Ruey-Kai Sheu, Chih-Wei Chung, Yen-Ching Wu, Chiao-Chi Ou, Chien-Wen Hsiao, Huang-Chen Chang, et al. "Application of Supervised Machine Learning to Recognize Competent Level and Mixed Antinuclear Antibody Patterns Based on ICAP International Consensus." Diagnostics 11, no. 4 (April 1, 2021): 642. http://dx.doi.org/10.3390/diagnostics11040642.
Повний текст джерелаАнотація:
Background: Antinuclear antibody pattern recognition is vital for autoimmune disease diagnosis but labor-intensive for manual interpretation. To develop an automated pattern recognition system, we established machine learning models based on the International Consensus on Antinuclear Antibody Patterns (ICAP) at a competent level, mixed patterns recognition, and evaluated their consistency with human reading. Methods: 51,694 human epithelial cells (HEp-2) cell images with patterns assigned by experienced medical technologists collected in a medical center were used to train six machine learning algorithms and were compared by their performance. Next, we choose the best performing model to test the consistency with five experienced readers and two beginners. Results: The mean F1 score in each classification of the best performing model was 0.86 evaluated by Testing Data 1. For the inter-observer agreement test on Testing Data 2, the average agreement was 0.849 (κ) among five experienced readers, 0.844 between the best performing model and experienced readers, 0.528 between experienced readers and beginners. The results indicate that the proposed model outperformed beginners and achieved an excellent agreement with experienced readers. Conclusions: This study demonstrated that the developed model could reach an excellent agreement with experienced human readers using machine learning methods.
13
Schuster, Stefan, and Silke Amtsfeld. "Template-matching describes visual pattern-recognition tasks in the weakly electric fishGnathonemus petersii." Journal of Experimental Biology 205, no. 4 (February 15, 2002): 549–57. http://dx.doi.org/10.1242/jeb.205.4.549.
Повний текст джерелаАнотація:
SUMMARYSeveral insects use template-matching systems to recognize objects or environmental landmarks by comparing actual and stored retinal images. Such systems are not viewpoint-invariant and are useful only when the locations in which the images have been stored and where they are later retrieved coincide. Here, we describe that a vertebrate, the weakly electric fish Gnathonemus petersii, appears to use template-matching to recognize visual patterns that it had previously viewed from a fixed vantage point. This fish is nocturnal and uses its electrical sense to find its way in the dark, yet it has functional vision that appears to be well adapted to dim light conditions. We were able to train three fish in a two-alternative forced-choice procedure to discriminate a rewarded from an unrewarded visual pattern. From its daytime shelter, each fish viewed two visual patterns placed at a set distance behind a transparent Plexiglas screen that closed the shelter. When the screen was lifted, the fish swam towards one of the patterns to receive a food reward or to be directed back into its shelter. Successful pattern discrimination was limited to low ambient light intensities of approximately 10 lx and to pattern sizes subtending a visual angle greater than 3°. To analyze the characteristics used by the fish to discriminate the visual training patterns, we performed transfer tests in which the training patterns were replaced by other patterns. The results of all such transfer tests can best be explained by a template-matching mechanism in which the fish stores the view of the rewarded training pattern and chooses from two other patterns the one whose retinal appearance best matches the stored view.
14
Ding, Shuxin, Tao Zhang, Ziyuan Liu, Rongsheng Wang, Sai Lu, Bin Xin, and Zhiming Yuan. "A Memetic Algorithm for High-Speed Railway Train Timetable Rescheduling." Journal of Advanced Computational Intelligence and Intelligent Informatics 26, no. 3 (May 20, 2022): 407–17. http://dx.doi.org/10.20965/jaciii.2022.p0407.
Повний текст джерелаАнотація:
This study addresses a high-speed railway train timetable rescheduling (TTR) problem with a complete blockage at the station and train operation constraints. The problem is formulated as a mixed-integer linear programming (MILP) model that minimizes the weighted sum of the total delay time of trains. A memetic algorithm (MA) is proposed, and the individual of MA is represented as a permutation of trains’ departure order at the disrupted station. The individual is decoded to a feasible schedule of the trains using a rule-based method to allocate the running time in sections and dwell time at stations. Consequently, the original problem is reformulated as an unconstrained problem. Several permutation-based operators are involved, including crossover, mutation, and local search. A restart strategy was employed to maintain the the population diversity. The proposed MA was compared with the first-scheduled-first-served (FSFS) algorithm and other state-of-the-art evolutionary algorithms. The experimental results demonstrate the superiority of MA in solving the TTR through permutation-based optimization in terms of constraint handling, solution quality, and computation time.
15
Kristiansen, Glen, and Matthias Schmid. "Application of computer‐generated images to train pattern recognition used in semiquantitative immunohistochemistry scoring." APMIS 130, no. 1 (November 25, 2021): 26–33. http://dx.doi.org/10.1111/apm.13188.
Повний текст джерела
16
Kao, Jehng-Jung. "A Xerion-based perl program to train a neural network for grid pattern recognition." Computers & Geosciences 22, no. 9 (November 1996): 1033–49. http://dx.doi.org/10.1016/s0098-3004(96)00042-8.
Повний текст джерела
17
Ali, Ashraf, Weam Samara, Doaa Alhaddad, Andrew Ware, and Omar A. Saraereh. "Human Activity and Motion Pattern Recognition within Indoor Environment Using Convolutional Neural Networks Clustering and Naive Bayes Classification Algorithms." Sensors 22, no. 3 (January 28, 2022): 1016. http://dx.doi.org/10.3390/s22031016.
Повний текст джерелаАнотація:
Human Activity Recognition (HAR) systems are designed to read sensor data and analyse it to classify any detected movement and respond accordingly. However, there is a need for more responsive and near real-time systems to distinguish between false and true alarms. To accurately determine alarm triggers, the motion pattern of legitimate users need to be stored over a certain period and used to train the system to recognise features associated with their movements. This training process is followed by a testing cycle that uses actual data of different patterns of activity that are either similar or different to the training data set. This paper evaluates the use of a combined Convolutional Neural Network (CNN) and Naive Bayes for accuracy and robustness to correctly identify true alarm triggers in the form of a buzzer sound for example. It shows that pattern recognition can be achieved using either of the two approaches, even when a partial motion pattern is derived as a subset out of a full-motion path.
18
Upadhyay, Ashutosh, and S. Vijayalakshmi. "Efficient Half Face Detection System Based on Linear Binary Pattern." Journal of Computational and Theoretical Nanoscience 17, no. 5 (May 1, 2020): 2342–48. http://dx.doi.org/10.1166/jctn.2020.8893.
Повний текст джерелаАнотація:
In the field of computer vision, face detection algorithms achieved accuracy to a great extent, but for the real time applications it remains a challenge to maintain the balance between the accuracy and efficiency i.e., to gain accuracy computational cost also increases to deal with the large data sets. This paper, propose half face detection algorithm to address the efficiency of the face detection algorithm. The full face detection algorithm consider complete face data set for training which incur more computation cost. To reduce the computation cost, proposed model captures the features of the half of the face by assuming that the human face is symmetric about the vertical axis passing through the nose and train the system using reduced half face features. The proposed algorithm extracts Linear Binary Pattern (LBP) features and train model using adaboost classifier. Algorithm performance is presented in terms of the accuracy i.e., True Positive Rate (TPR), False Positive Rate (FTR) and face recognition time complexity.
19
Tang, Ying Jie, Ying Jun Tang, and Xin Liang Xie. "The New Identification Method for Low Frequency Oscillation Mode in Power System Based on Prony Algorithm and Neural Network." Applied Mechanics and Materials 321-324 (June 2013): 1400–1404. http://dx.doi.org/10.4028/www.scientific.net/amm.321-324.1400.
Повний текст джерелаАнотація:
This paper presented a new improved Prony algorithm based on neural network to train weights.The algorithm solved some problems that difficulty and low precision during matrix inversion in Prony method. According to real-time transform characteristics of low frequency oscillation in power system, the algorithm used limited data windows in on-line parameter estimation and pattern recognition, and improved pattern recognition precision. The simulation results proved that this proposal algorithm has some features of directly ,effective, high reliability, less calculation amount and minor error when it be used to analysis oscillation characteristics and mode identification. So it is suitable for identification of low frequency oscillation mode in power system.
20
Cao, Chenxing, Bai Shan, and Haiyan Zhang. "Pattern Recognition of Wushu Routine Action Decomposition Process Based on Kinect." Mathematical Problems in Engineering 2022 (August 27, 2022): 1–11. http://dx.doi.org/10.1155/2022/3876487.
Повний текст джерелаАнотація:
Human action recognition is a hotspot in the fields of computer vision and pattern recognition. Human action recognition technology has created huge social value and considerable economic value for the society. Meeting people’s needs and understanding people’s expressions are the current research focus. Aiming at the problem that the movement cannot be continuously identified and due to a lack of detailed features in the action decomposition pattern recognition in the traditional Wushu routine decomposition process, it is proposed to use Kinect technology to identify the Wushu routine movement decomposition process in the Wushu routine movement decomposition process. This paper analyzes the principle of skeleton tracking and skeleton extraction performed by the Kinect human sensor and uses the Kinect sensor with the Visual Studio 2015 development platform to collect and process the skeleton data of limb movements and defines eight static limb motion samples and four dynamic limbs. The study uses a deep learning neural network algorithm to train and identify the established database of static body movements and uses the same template matching algorithm and K-NN. The recognition effects of the algorithms were compared and analyzed, and it was concluded that the static body motion recognition rates of the three algorithms were all above 90%. In this paper, recognition experiments are carried out on the MSR action 3D database. The influence of different integrated decision-making methods on the recognition results is further discussed and analyzed, and the average method integrated decision-making, which is most suitable for the algorithm model in this paper, is proposed. The results show that the recognition accuracy of the algorithm reaches 98.1%, which proves the feasibility of the preprocessing algorithm.
21
Liu, Xiaobo, Xu Yin, Min Wang, Yaoming Cai, and Guang Qi. "Emotion Recognition Based on Multi-Composition Deep Forest and Transferred Convolutional Neural Network." Journal of Advanced Computational Intelligence and Intelligent Informatics 23, no. 5 (September 20, 2019): 883–90. http://dx.doi.org/10.20965/jaciii.2019.p0883.
Повний текст джерелаАнотація:
In human-machine interaction, facial emotion recognition plays an important role in recognizing the psychological state of humans. In this study, we propose a novel emotion recognition framework based on using a knowledge transfer approach to capture features and employ an improved deep forest model to determine the final emotion types. The structure of a very deep convolutional network is learned from ImageNet and is utilized to extract face and emotion features from other data sets, solving the problem of insufficiently labeled samples. Then, these features are input into a classifier called multi-composition deep forest, which consists of 16 types of forests for facial emotion recognition, to enhance the diversity of the framework. The proposed method does not need require to train a network with a complex structure, and the decision tree-based classifier can achieve accurate results with very few parameters, making it easier to implement, train, and apply in practice. Moreover, the classifier can adaptively decide its model complexity without iteratively updating parameters. The experimental results for two emotion recognition problems demonstrate the superiority of the proposed method over several well-known methods in facial emotion recognition.
22
Vazquez, Roberto A., and Beatriz A. Garro. "Training Spiking Neural Models Using Artificial Bee Colony." Computational Intelligence and Neuroscience 2015 (2015): 1–14. http://dx.doi.org/10.1155/2015/947098.
Повний текст джерелаАнотація:
Spiking neurons are models designed to simulate, in a realistic manner, the behavior of biological neurons. Recently, it has been proven that this type of neurons can be applied to solve pattern recognition problems with great efficiency. However, the lack of learning strategies for training these models do not allow to use them in several pattern recognition problems. On the other hand, several bioinspired algorithms have been proposed in the last years for solving a broad range of optimization problems, including those related to the field of artificial neural networks (ANNs). Artificial bee colony (ABC) is a novel algorithm based on the behavior of bees in the task of exploring their environment to find a food source. In this paper, we describe how the ABC algorithm can be used as a learning strategy to train a spiking neuron aiming to solve pattern recognition problems. Finally, the proposed approach is tested on several pattern recognition problems. It is important to remark that to realize the powerfulness of this type of model only one neuron will be used. In addition, we analyze how the performance of these models is improved using this kind of learning strategy.
23
Cai, Yongxiang, Jingwen Gao, Gen Zhang, and Yuangang Liu. "Efficient facial expression recognition based on convolutional neural network." Intelligent Data Analysis 25, no. 1 (January 26, 2021): 139–54. http://dx.doi.org/10.3233/ida-194965.
Повний текст джерелаАнотація:
The goal of research in Facial Expression Recognition (FER) is to build a robust and strong recognizability model. In this paper, we propose a new scheme for FER systems based on convolutional neural network. Part of the regular convolution operation is replaced by depthwise separable convolution to reduce the number of parameters and the computational workload; the self-adaption joint loss function is adopted to improve the classification performance. In addition, we balance our train set through data augmentation, and we preprocess the input images through illumination processing, face detection, and other methods, effectively maximizing the expression recognition rate. Experiments to validate our methods are conducted based on the TensorFlow platform and Fer2013 dataset. We analyze the experimental results before and after train set balancing and network model modification, and we compare our results with those of other researchers. The results show that our method is effective at increasing the expression recognition rate under the same experiment conditions. We further conduct an experiment on our own expression dataset relevant to driving safety, and it yields similar results.
24
Li, Xiaofeng, Limin Jia, and Xin Yang. "Fault Diagnosis of Train Axle Box Bearing Based on Multifeature Parameters." Discrete Dynamics in Nature and Society 2015 (2015): 1–8. http://dx.doi.org/10.1155/2015/846918.
Повний текст джерелаАнотація:
Failure of the train axle box bearing will cause great loss. Now, condition-based maintenance of train axle box bearing has been a research hotspot around the world. Vibration signals generated by train axle box bearing have nonlinear and nonstationary characteristics. The methods used in traditional bearing fault diagnosis do not work well with the train axle box. To solve this problem, an effective method of axle box bearing fault diagnosis based on multifeature parameters is presented in this paper. This method can be divided into three parts, namely, weak fault signal extraction, feature extraction, and fault recognition. In the first part, a db4 wavelet is employed for denoising the original signals from the vibration sensors. In the second part, five time-domain parameters, five IMF energy-torque features, and two amplitude-ratio features are extracted. The latter seven frequency domain features are calculated based on the empirical mode decomposition and envelope spectrum analysis. In the third part, a fault classifier based on BP neural network is designed for automatic fault pattern recognition. A series of tests are carried out to verify the proposed method, which show that the accuracy is above 90%.
25
Fang, Huijuan, Yongji Wang, and Jiping He. "Spiking Neural Networks for Cortical Neuronal Spike Train Decoding." Neural Computation 22, no. 4 (April 2010): 1060–85. http://dx.doi.org/10.1162/neco.2009.10-08-885.
Повний текст джерелаАнотація:
Recent investigation of cortical coding and computation indicates that temporal coding is probably a more biologically plausible scheme used by neurons than the rate coding used commonly in most published work. We propose and demonstrate in this letter that spiking neural networks (SNN), consisting of spiking neurons that propagate information by the timing of spikes, are a better alternative to the coding scheme based on spike frequency (histogram) alone. The SNN model analyzes cortical neural spike trains directly without losing temporal information for generating more reliable motor command for cortically controlled prosthetics. In this letter, we compared the temporal pattern classification result from the SNN approach with results generated from firing-rate-based approaches: conventional artificial neural networks, support vector machines, and linear regression. The results show that the SNN algorithm can achieve higher classification accuracy and identify the spiking activity related to movement control earlier than the other methods. Both are desirable characteristics for fast neural information processing and reliable control command pattern recognition for neuroprosthetic applications.
26
Mazakov, T. Zh, and D. N. Narynbekovna. "DEVELOPMENT OF BIOMETRIC METHODS AND INFORMATION SECURITY TOOLS." PHYSICO-MATHEMATICAL SERIES 2, no. 336 (April 15, 2021): 121–24. http://dx.doi.org/10.32014/2021.2518-1726.30.
Повний текст джерелаАнотація:
Now a day’s security is a big issue, the whole world has been working on the face recognition techniques as face is used for the extraction of facial features. An analysis has been done of the commonly used face recognition techniques. This paper presents a system for the recognition of face for identification and verification purposes by using Principal Component Analysis (PCA) with Back Propagation Neural Networks (BPNN) and the implementation of face recognition system is done by using neural network. The use of neural network is to produce an output pattern from input pattern. This system for facial recognition is implemented in MATLAB using neural networks toolbox. Back propagation Neural Network is multi-layered network in which weights are fixed but adjustment of weights can be done on the basis of sigmoidal function. This algorithm is a learning algorithm to train input and output data set. It also calculates how the error changes when weights are increased or decreased. This paper consists of background and future perspective of face recognition techniques and how these techniques can be improved.
27
Apriani, Nurlia, Rita Wiryasaputra, and Lastri Widya Astuti. "PENGENALAN POLA SUARA MANUSIA BEREKSTENSI FILE WAV MENGGUNAKAN METODE FAST FOURIER TRANSFORM DAN BAYES." Computatio : Journal of Computer Science and Information Systems 2, no. 1 (May 22, 2018): 1. http://dx.doi.org/10.24912/computatio.v2i1.1025.
Повний текст джерелаАнотація:
The human voice is a very unique sound wave. That's because every human being has a different kind of sound wave. The fundamental difference in human voice is high the low the sound level associated with the signal from sound waves. The purpose of this research is to know the accuracy result from Fast Fourier Transform and Bayes method in pattern recognition. The Fast Fourier Transform method is used for feature extraction and Bayes method is used to calculate the sound probability value between the train data and test data, then Bayes Method is used to determine the result of the introduction of some previously stored train data. This research was made using Matlab R2016a, by matching the pattern of human sound that has been made before or called train data with new sound pattern or called test data. Testing is done on voice in the database and the voice is not in the database. Test results for voice in the database were 96% for first men and 76% for first women. While testing for voice is not in the database is 46% for second men and 50% for second women
28
Yin, Zeyu, Jianbin Zheng, Liping Huang, Yifan Gao, Huihui Peng, and Linghan Yin. "SA-SVM-Based Locomotion Pattern Recognition for Exoskeleton Robot." Applied Sciences 11, no. 12 (June 16, 2021): 5573. http://dx.doi.org/10.3390/app11125573.
Повний текст джерелаАнотація:
An exoskeleton robot is a kind of wearable mechanical instrument designed according to the shape and function of the human body. The main purpose of its design and manufacture is to enhance human strength, assist human walking and to help patients recover. The walking state of the exoskeleton robot should be highly consistent with the state of the human, so the accurate locomotion pattern recognition is the premise of the flexible control of the exoskeleton robot. In this paper, a simulated annealing (SA) algorithm-based support vector machine model is proposed for the recognition of different locomotion patterns. In order to improve the overall performance of the support vector machine (SVM), the simulated annealing algorithm is adopted to obtain the optimal parameters of support vector machine. The pressure signal measured by the force sensing resistors integrated on the sole of the shoe is fused with the position and pose information measured by the inertial measurement units attached to the thigh, shank and foot, which are used as the input information of the support vector machine. The max-relevance and min-redundancy algorithm was selected for feature extraction based on the window size of 300 ms and the sampling frequency of 100 Hz. Since the signals come from different types of sensors, normalization is required to scale the input signals to the interval (0,1). In order to prevent the classifier from overfitting, five layers of cross validation are used to train the support vector machine classifier. The support vector machine model was obtained offline in MATLAB. The finite state machine is used to limit the state transition and improve the recognition accuracy. Experiments on different locomotion patterns show that the accuracy of the algorithm is 97.47% ± 1.16%. The SA-SVM method can be extended to industrial robots and rehabilitation robots.
29
Majdi, Hasan Shakir, Sameera Sadey Shijer, Abduljabbar Owaid Hanfesh, Laith Jaafer Habeeb, and Ahmad H. Sabry. "Analysis of fault diagnosis of DC motors by power consumption pattern recognition." Eastern-European Journal of Enterprise Technologies 5, no. 5 (113) (October 31, 2021): 14–20. http://dx.doi.org/10.15587/1729-4061.2021.240262.
Повний текст джерелаАнотація:
Early detection of faults in DC motors extends their life and lowers their power usage. There are a variety of traditional and soft computing techniques for detecting faults in DC motors. Many diagnostic techniques have been developed in the past to detect such fault-related patterns. These methods for detecting the aforementioned potential failures of motors can be utilized in a variety of scientific and technological domains. Motor Power Pattern Analysis (MPPA) is a technology that analyzes the current and voltage provided to an electric motor using particular patterns and protocols to assess the operational status of the motors without disrupting production. Engineers and researchers, particularly in industries, face a difficult challenge in monitoring spinning types of equipment. In this work, we are going to explain how to use the motor power pattern/signature analysis (MPPA) of a power signal driving a servo to find mechanical defects in a gear train. A hardware setup is used to simplify the demonstration of obtaining spectral metrics from the power consumption signals. A DC motor, a set of metal or nylon drive gears, and a control circuit are employed. The speed control circuit was eliminated to allow direct monitoring of the DC motor's current profiles. Infrared (IR) photo-interrupters with a 35 mm diameter, eight-holed, standard servo wheel were employed to gather the tachometer signal at the servo's output. The mean value of the measurements was 318 V for the healthy profile, while it was 330 V for the faulty gears power data. The proposed power consumption profile analysis approach succeeds to recognize the mechanical faults in the gear-box of a DC servomotor via examining the mean level of the power consumption pattern as well as the extraction of the Power Spectral Density (PSD) through comparing faulty and healthy profiles
30
Gorobсhenko, O. "THEORETICAL FUNDAMENTALS OF ESTIMATABILITY ASSESSMENT OF TRAIN SITUATION SIGNS FOR WORK OF INTELLECTUAL LOCOMOTIVE CONTROL SYSTEMS." Collection of scientific works of the State University of Infrastructure and Technologies series "Transport Systems and Technologies" 1, no. 38 (December 24, 2021): 223–31. http://dx.doi.org/10.32703/2617-9040-2021-38-220-21.
Повний текст джерелаАнотація:
The article is devoted to the problem of implementation of intelligent control systems in transport. An important task is to assess the information parameters of the control systems. In the existing works the question of definition of one of the basic parameters of functioning of locomotive control systems - information value of separate signs of a train situation is not considered. This does not make it possible to determine the order of signal processing at the input and assess their contribution to the adoption of a control decision. Moreover, informativeness is a relative value, which is expressed in the different information value of a particular feature for the classification of different train situations. Also, the informativeness of the feature may depend on the type of decisive rules in the classification procedure. The quality of recognition of a train situation in which the locomotive crew is, depends on the quality of the features used by the classification system. The decisive criterion for the informativeness of the features in the problem of pattern recognition is the magnitude of losses from errors. To determine the range of the most informative features of train situations, the method of random search with adaptation was used. The results of the work make it possible to optimize the operation of automated and intelligent train control systems by reducing the amount of calculations and simplifying their algorithm.
31
Gorobchenko, O. "DEVELOPMENT OF THE METHOD OF CLUSTERIZATION OF TRAIN SITUATIONS." Collection of scientific works of the State University of Infrastructure and Technologies series "Transport Systems and Technologies" 1, no. 37 (June 29, 2021): 187–95. http://dx.doi.org/10.32703/2617-9040-2021-37-18.
Повний текст джерелаАнотація:
The introduction of intelligent locomotive control systems requires better approaches to assessing and monitoring the current train situation than those used in modern traction rolling stock. Automatic detection of complex abnormal situations is currently not provided. For example, determining the inefficiency of the brakes, speeding, the presence of obstacles or people on the track, the deterioration of the traction properties of rolling stock, etc. relies solely on the driver of the locomotive. Given the important impact of these factors on traffic safety, it is proposed to include in the functions of automated and intelligent traffic control systems recognition of abnormal situations and notification of its occurrence. When driving a train, all objects of classification (train situations) are divided into a finite number of classes. A finite number of precedent objects are known and studied for each class. The task of pattern recognition is to assign a new recognizable situation to a class. The classifier or decisive rule is the rule of assigning the image of a train situation to one of the classes on the basis of its vector of features. An order of classification of train situations has been developed, which allows to allocate clusters of any complex shape, provided that different parts of such clusters are connected by chains of close to each other elements. The measure of difference is the square of the Euclidean distance.
32
Andrian, Rian, and Rizki Hikmawan. "The Importance of Computational Thinking to Train Structured Thinking in Problem Solving." Jurnal Online Informatika 6, no. 1 (June 17, 2021): 113. http://dx.doi.org/10.15575/join.v6i1.677.
Повний текст джерелаАнотація:
Ability to do problem solving will be greatly influenced by how the flow of thinking in decomposing a problem until it finds the root of the problem so that it can determine the best solution. There is currently a growing recognition around the world that all fields require a prerequisite ability, namely to think logically, in a structured manner, and use computational tools to rapidly model and visualize data. This ability is known as Computational Thinking (CT). In this study, the author applied the computational thinking key concept in a case study to train structured thinking in problem solving. Computational thinking key concept includes Decomposition, Pattern recognition, Abstraction, and lastly use algorithms when they design simple steps to solve problems. Based on our case study that has been model, the result shows us that Computational Thinking can be used to train structured thinking in problem solving in everyday life
33
Cheng, Shuo, and Guohui Zhou. "Facial Expression Recognition Method Based on Improved VGG Convolutional Neural Network." International Journal of Pattern Recognition and Artificial Intelligence 34, no. 07 (October 22, 2019): 2056003. http://dx.doi.org/10.1142/s0218001420560030.
Повний текст джерелаАнотація:
Because the shallow neural network has limited ability to represent complex functions with limited samples and calculation units, its generalization ability will be limited when it comes to complex classification problems. The essence of deep learning is to learn a nonlinear network structure, to represent input data distributed representation and demonstrate a powerful ability to learn deeper features of data from a small set of samples. In order to realize the accurate classification of expression images under normal conditions, this paper proposes an expression recognition model of improved Visual Geometry Group (VGG) deep convolutional neural network (CNN). Based on the VGG-19, the model optimizes network structure and network parameters. Most expression databases are unable to train the entire network from the start due to lack of sufficient data. This paper uses migration learning techniques to overcome the shortage of image training samples. Shallow CNN, Alex-Net and improved VGG-19 deep CNN are used to train and analyze the facial expression data on the Extended Cohn–Kanade expression database, and compare the experimental results obtained. The experimental results indicate that the improved VGG-19 network model can achieve 96% accuracy in facial expression recognition, which is obviously superior to the results of other network models.
34
Drobac, Senka, and Krister Lindén. "Optical character recognition with neural networks and post-correction with finite state methods." International Journal on Document Analysis and Recognition (IJDAR) 23, no. 4 (August 20, 2020): 279–95. http://dx.doi.org/10.1007/s10032-020-00359-9.
Повний текст джерелаАнотація:
Abstract The optical character recognition (OCR) quality of the historical part of the Finnish newspaper and journal corpus is rather low for reliable search and scientific research on the OCRed data. The estimated character error rate (CER) of the corpus, achieved with commercial software, is between 8 and 13%. There have been earlier attempts to train high-quality OCR models with open-source software, like Ocropy (https://github.com/tmbdev/ocropy) and Tesseract (https://github.com/tesseract-ocr/tesseract), but so far, none of the methods have managed to successfully train a mixed model that recognizes all of the data in the corpus, which would be essential for an efficient re-OCRing of the corpus. The difficulty lies in the fact that the corpus is printed in the two main languages of Finland (Finnish and Swedish) and in two font families (Blackletter and Antiqua). In this paper, we explore the training of a variety of OCR models with deep neural networks (DNN). First, we find an optimal DNN for our data and, with additional training data, successfully train high-quality mixed-language models. Furthermore, we revisit the effect of confidence voting on the OCR results with different model combinations. Finally, we perform post-correction on the new OCR results and perform error analysis. The results show a significant boost in accuracy, resulting in 1.7% CER on the Finnish and 2.7% CER on the Swedish test set. The greatest accomplishment of the study is the successful training of one mixed language model for the entire corpus and finding a voting setup that further improves the results.
35
Huang, Ping, Zhongcan Li, Chao Wen, Javad Lessan, Francesco Corman, and Liping Fu. "Modeling train timetables as images: A cost-sensitive deep learning framework for delay propagation pattern recognition." Expert Systems with Applications 177 (September 2021): 114996. http://dx.doi.org/10.1016/j.eswa.2021.114996.
Повний текст джерела
36
Zhang, Lin. "Face Gender Recognition Research Based on Local Features and Support Vector Machine." Applied Mechanics and Materials 687-691 (November 2014): 3714–17. http://dx.doi.org/10.4028/www.scientific.net/amm.687-691.3714.
Повний текст джерелаАнотація:
In this paper, we proposed a face gender recognition method based on local features and SVM. First, we divide the face image into five parts which are used to instead of the whole face for better recognition performance. Second, we use CS to extract local features of these five parts. Then, we respectively train five single SVM classifiers to achieve one to one feature recognition for local features. Finally, decision information fusion is used to achieve the final classification. Because SVM were successfully used to solve numerous pattern recognition problems and is mainly used to solve two-classification problem, selecting SVM to do gender recognition in our method has the obvious superiority. After a lot of experiments, results show that the proposed method in this paper is stable and effective, greatly improving the efficiency of face gender recognition.
37
Abdel-Karim, Benjamin M. "Beautiful Fractals as a Crystal Ball for Financial Markets? - Investment Decision Support System Based on Image Recognition Using Artificial Intelligence." Journal of Prediction Markets 14, no. 2 (December 11, 2020): 27–44. http://dx.doi.org/10.5750/jpm.v14i2.1804.
Повний текст джерелаАнотація:
The work by Mandelbrot develops a basic understanding of fractals and the artwork of Jackson Pollok to reveal the beauty fractal geometry. The pattern of recurring structures is also reflected in share prices. Mandelbrot himself speaks of the fractal heart of the financial markets. Previous research has shown the potential of image recognition. This paper presents the possibility of using the structure recognition capability of modern machine learning methods to make forecasts based on fractal course information. We generate training data from real and simulated data. These data are represented in images to train a special artificial neural network. Subsequently, real data are presented to the network for use in predicting. The results show that the forecast of time series based on stock price illustration, compared to a benchmark, delivers promising results. This paper makes two essential contributions to research. From a theoretical point of view, fractal geometry shows that it can serve as a means of legitimation for technical analysis. From a practical point of view, highly developed methods from the field of machine learning are able to recognize patterns in data through appropriate data transformation, and that models such as random walk have an informational content that can be used to train machine learning models.
38
Zhang, Li Xia, Fu Zhou Feng, Peng Cheng Jiang, and Xu Chang Wang. "Application of Neural Network on Acoustic Signal Identification." Applied Mechanics and Materials 151 (January 2012): 523–26. http://dx.doi.org/10.4028/www.scientific.net/amm.151.523.
Повний текст джерелаАнотація:
The application based on Backpropagation (BP) Algorithm network is conducted on identifying the categories and numbers of mechanical equipments by acoustic signal in battlefield targets. Collected signal was pre-processed and extracted the power spectrum feature of acoustic signal as input vectors of neural networks, then classified by neural networks and pattern recognition theorem. We employ the acoustic signals of six kinds of normal equipments as training samples to train the network. The experiment shows that the ratio of recognition of the acoustic signal processing system based on neural networks proposed is better than the conventional methods.
39
OBERHOFF, DANIEL, and MARINA KOLESNIK. "NEURAL OBJECT RECOGNITION BY HIERARCHICAL APPEARANCE LEARNING." International Journal of Pattern Recognition and Artificial Intelligence 22, no. 05 (August 2008): 883–97. http://dx.doi.org/10.1142/s0218001408006582.
Повний текст джерелаАнотація:
We present a system for object recognition that is largely inspired by physiologically identified processing streams in the visual cortex, specifically in the ventral stream. It consists of neural units organized in a hierarchy of layers with encoding features of increasing complexity. A key feature of the system is that the neural units learn their preferred patterns from visual input alone. Through this "soft wiring" of neural units the system becomes tuned for target object classes through passive visual experience and no labels are required in this stage. Object labels are only introduced in the last step to train a classifier on the system's output. While this tuning process is purely feed-forward we also present a neural mechanism for back projection of the learned image patterns down the hierarchical layers, and demonstrate how this feedback can be used to stabilize the system in the presence of noise. We test the neural system with natural images from publicly available data-sets of natural scenes and handwritten digits.
40
Mota, Mariana R. F., Pedro H. L. Silva, Eduardo J. S. Luz, Gladston J. P. Moreira, Thiago Schons, Lauro A. G. Moraes, and David Menotti. "A deep descriptor for cross-tasking EEG-based recognition." PeerJ Computer Science 7 (May 19, 2021): e549. http://dx.doi.org/10.7717/peerj-cs.549.
Повний текст джерелаАнотація:
Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.
41
Guo, Yuliang. "Pattern Recognition and Neural Network-Driven Roller Track Analysis via 5G Network." Mobile Information Systems 2020 (December 30, 2020): 1–8. http://dx.doi.org/10.1155/2020/6675140.
Повний текст джерелаАнотація:
Roller skating is an important and international physical exercise, which has beautiful body movements to be watched. However, the falling of roller athletes also happens frequently. Upon the roller athletes’ fall, it means that the whole competition is over and even the roller athletes are perhaps injured. In order to stave off the tragedy, the roller track can be analyzed and be notified the roller athlete to terminate the competition. With such consideration, this paper analyzes the roller track by using two advanced technologies, i.e., pattern recognition and neural network, in which each roller athlete is equipped with an automatic movement identifier (AMI). Meanwhile, AMI is connected with the remote video monitor referee via the transmission of 5G network. In terms of AMI, its function is realized by pattern recognition, including data collection module, data processing module, and data storage module. Among them, the data storage module considers the data classification based on roller track. In addition, the neural network is used to train the roller tracks stored at AMI and give the further analysis results for the remote video monitor referee. Based on NS3, the devised AMI is simulated and the experimental results reveal that the prediction accuracy can reach 100% and the analyzed results can be used for the falling prevention timely.
42
Sokhandan, Negin, Nesreen Ziedan, Ali Broumandan, and Gérard Lachapelle. "Context-Aware Adaptive Multipath Compensation Based on Channel Pattern Recognition for GNSS Receivers." Journal of Navigation 70, no. 5 (April 10, 2017): 944–62. http://dx.doi.org/10.1017/s0373463317000121.
Повний текст джерелаАнотація:
The possibility of identifying the type of multipath environment and receiver motion (e.g. pedestrian, vehicular) using pattern recognition approaches based on multipath parameters is investigated. This allows the receiver to adjust its tracking strategy and optimally tune its tracking parameters to mitigate code multipath effects. A Support Vector Machine (SVM) classification method with a modified Gaussian kernel is applied in this approach. A set of temporal and spectral features is extracted from the correlation samples of the received signals in different environments to train the classifier. The latter is then used in the structure of stochastic gradient-based adaptive multipath compensation and tracking techniques to tune the signal tracking parameters based on the environment and receiver motion. Simulation and real data measurements using Galileo E1B/C signals are performed to assess the validity of the proposed environment identification approaches and to evaluate the impact of the proposed context-based receiver parameter tuning techniques on tracking performance in multipath environments. Test results showed that the proposed classifiers have an accuracy between 86% and 92%, and the tracking performance improved by about 15%.
43
Wahyudi, Irfan, Chandra Prasetyo Utomo, Samsuridjal Djauzi, Muhamad Fathurahman, Gerhard Reinaldi Situmorang, Arry Rodjani, Kevin Yonathan, and Budi Santoso. "Digital Pattern Recognition for the Identification of Various Hypospadias Parameters via an Artificial Neural Network: Protocol for the Development and Validation of a System and Mobile App." JMIR Research Protocols 11, no. 11 (November 25, 2022): e42853. http://dx.doi.org/10.2196/42853.
Повний текст джерелаАнотація:
Background Hypospadias remains the most prevalent congenital abnormality in boys worldwide. However, the limited infrastructure and number of pediatric urologists capable of diagnosing and managing the condition hinder the management of hypospadias in Indonesia. The use of artificial intelligence and image recognition is thought to be beneficial in improving the management of hypospadias cases in Indonesia. Objective We aim to develop and validate a digital pattern recognition system and a mobile app based on an artificial neural network to determine various parameters of hypospadias. Methods Hypospadias and normal penis images from an age-matched database will be used to train the artificial neural network. Images of 3 aspects of the penis (ventral, dorsal, and lateral aspects, which include the glans, shaft, and scrotum) will be taken from each participant. The images will be labeled with the following hypospadias parameters: hypospadias status, meatal location, meatal shape, the quality of the urethral plate, glans diameter, and glans shape. The data will be uploaded to train the image recognition model. Intrarater and interrater analyses will be performed, using the test images provided to the algorithm. Results Our study is at the protocol development stage. A preliminary study regarding the system’s development and feasibility will start in December 2022. The results of our study are expected to be available by the end of 2023. Conclusions A digital pattern recognition system using an artificial neural network will be developed and designed to improve the diagnosis and management of patients with hypospadias, especially those residing in regions with limited infrastructure and health personnel. International Registered Report Identifier (IRRID) PRR1-10.2196/42853
44
S*, Suni S., and K. Gopakumar. "Extracting Multiple Features for Dynamic Hand Gesture Recognition." International Journal of Engineering and Advanced Technology 10, no. 4 (April 30, 2021): 71–75. http://dx.doi.org/10.35940/ijeat.d2343.0410421.
Повний текст джерелаАнотація:
In this work a framework based on histogram of orientation of optical flow (HOOF) and local binary pattern from three orthogonal planes (LBP_TOP) is proposed for recognizing dynamic hand gestures. HOOF algorithm extracts local shape and dynamic motion information of gestures from image sequences and local descriptor LBP is extended to three orthogonal planes to create an efficient motion descriptor. These features are invariant to scale, translation, illumination and direction of motion. The performance of the new framework is tested in two different ways. The first one is by fusing the global and local features as one descriptor and the other is using features separately to train the multi class support vector machine. Performance analysis shows that the proposed approach produces better results for recognizing dynamic hand gestures when compared with state of the art methods
45
Xu, Hang Fei, Hong Yan Chen, and Kun Yuan. "A BP Neural Network-Based Automatic Windshield Wiper Controller." Advanced Materials Research 482-484 (February 2012): 31–34. http://dx.doi.org/10.4028/www.scientific.net/amr.482-484.31.
Повний текст джерелаАнотація:
This paper introduces a method of constructing the control model of automatic windshield wiper based on BP neural network. A model of pattern recognition based on BP neural network is built and train it with specialists’ experience data, and then tested it. The result indicates that this model based on BP neural network is effective to handle uncertainties and nonlinearities of the automatic windshield wiper system, without use of a sophisticated mathematical model.
46
Ali, Haider, Umair Ullah Tariq, and Muhammad Abid. "Learning Discriminating Features for Gender Recognition of Real World Faces." International Journal of Image and Graphics 14, no. 03 (July 2014): 1450011. http://dx.doi.org/10.1142/s0219467814500119.
Повний текст джерелаАнотація:
The automatic gender recognition of faces has many applications, for example surveillance, targeted advertisement and human computer interaction, etc. Humans have the ability to accurately determine the gender from faces, however, for a machine, it is a difficult task. Many studies have targeted this problem, but most of these studies have used images taken under constrained conditions. In Real-world systems have to process images with wide variations in lighting and pose that makes the classification task very challenging. We have analyzed the gender classification of real world faces. Faces from images are detected, aligned and represented using local binary pattern histograms. Adaptive boosting selects the discriminating features and boosted LBP features are used to train a support vector machine that provides a recognition rate of 95.5%.
47
Puissant, Stephane. "Taxonomy, distribution and first eco-ethological data of Melampsalta varipes (Waltl, 1837), an unrecognized cicada (Hemiptera, Cicadidae)." Insect Systematics & Evolution 36, no. 3 (2005): 301–15. http://dx.doi.org/10.1163/187631205788838401.
Повний текст джерелаАнотація:
AbstractThe west Palaearctic cicada Melampsalta varipes (Waltl, 1837) has been studied for the first time in Spain. After a summary of its taxonomy and the designation of a neotype, its distribution and habitat in Spain and Portugal are given. M. varipes can be considered as a typical Mediterranean cicada essentially found in open fields, i.e. with low percentage of ligneous plants. The increase of tourism activities and the abrupt agricultural practice modification probably modify its habitat endangering the populations. Males call either when static on a perch or in flight. The song is attractive to both sexes, one singing male stimulating a chorus from surrounding males. The calling song consists of monotonous trains of short echeme and long echeme. Each echeme is composed of two parts: a successive short train of pulses and a sustained train of pulses. The structure of the signal varied among individuals in both temporal and frequency parameters suggesting individual acoustic markers. The duration of the inter-echeme silence may act as a simple specific recognition process. The frequency pattern show two groups of frequencies which could guide the female over long distances to males and then help them to localize males at close range.
48
Wang, Wenqi, Vaneet Aggarwal, and Shuchin Aeron. "Principal component analysis with tensor train subspace." Pattern Recognition Letters 122 (May 2019): 86–91. http://dx.doi.org/10.1016/j.patrec.2019.02.024.
Повний текст джерела
49
Dieste-Velasco, M. Isabel. "Application of a Pattern-Recognition Neural Network for Detecting Analog Electronic Circuit Faults." Mathematics 9, no. 24 (December 15, 2021): 3247. http://dx.doi.org/10.3390/math9243247.
Повний текст джерелаАнотація:
In this study, machine learning techniques based on the development of a pattern–recognition neural network were used for fault diagnosis in an analog electronic circuit to detect the individual hard faults (open circuits and short circuits) that may arise in a circuit. The ability to determine faults in the circuit was analyzed through the availability of a small number of measurements in the circuit, as test points are generally not accessible for verifying the behavior of all the components of an electronic circuit. It was shown that, despite the existence of a small number of measurements in the circuit that characterize the existing faults, the network based on pattern-recognition functioned adequately for the detection and classification of the hard faults. In addition, once the neural network has been trained, it can be used to analyze the behavior of the circuit versus variations in its components, with a wider range than that used to develop the neural network, in order to analyze the ability of the ANN to predict situations different from those used to train the ANN and to extract valuable information that may explain the behavior of the circuit.
50
Wan, Yuanfang, Zishan Han, Jun Zhong, and Guohua Chen. "Pattern recognition and bionic manipulator driving by surface electromyography signals using convolutional neural network." International Journal of Advanced Robotic Systems 15, no. 5 (September 1, 2018): 172988141880213. http://dx.doi.org/10.1177/1729881418802138.
Повний текст джерелаАнотація:
With the development of robotics, intelligent neuroprosthesis for amputees is more concerned. Research of robot controlling based on electrocardiogram, electromyography, and electroencephalogram is a hot spot. In medical research, electrode arrays are commonly used as sensors for surface electromyograms. Although these sensors collect more accurate data and sampling at higher frequencies, they have no advantage in terms of portability and ease of use. In recent years, there are also some small surface electromyography sensors for research. The portability of the sensor and the calculation speed of the calculation method directly affect the development of the bionic prosthesis. A consumer-grade surface electromyography device is selected as surface electromyography sensor in this study. We first proposed a data structure to convert raw surface electromyography signals from an array structure into a matrix structure (we called it surface electromyography graph). Then, a convolutional neural network was used to classify it. Discrete surface electromyography signals recorded from three persons 14 gestures (widely used in other research to evaluate the performance of classifier) have been applied to train the classifier and we get an accuracy of 97.27%. The impacts of different components used in convolutional neural network were tested with this data, and subsequently, the best results were selected to build the classifier used in this article. The NinaPro database 5 (one of the biggest surface electromyography data sets) was also used to evaluate our method, which comprises of hand movement data of 10 intact subjects with two myo armbands as sensors, and the classification accuracy increased by 13.76% on average when using double myo armbands and increased by 18.92% on average when using single myo armband. In order to driving the robot hand (bionic manipulator), a group of continuous surface electromyography signals was recorded to train the classifier, and an accuracy of 91.72% was acquired. We also used the same method to collect a set of surface electromyography data from a disabled with hand lost, then classified it using the abovementioned network and achieved an accuracy of 89.37%. Finally, the classifier was deployed to the microcontroller to drive the bionic manipulator, and the full video URL is given in the conclusion, with both the healthy man and the disabled tested with the bionic manipulator. The abovementioned results suggest that this method will help to facilitate the development and application of surface electromyography neuroprosthesis.