Recognition Problem Research Articles

Grapevine Branch Recognition and Pruning Point Localization Technology Based on Image Processing

The identification of branches and bud points is the key to intelligent pruning of dormant grapevine branches and precise positioning of the pruning point on the branch is an important prerequisite for robotic arm pruning. This study takes Cabernet Sauvignon wine grapes as the experimental object and proposes a depth image-based pruning point localization algorithm based on pruning rules. In order to solve the problem of bud recognition in complex backgrounds, this study adopts a detection method that combines semantic segmentation and target detection. Firstly, the semantic segmentation algorithm PSP-net is used to separate the branches and the main stem from the background and the separated image undergoes two kinds of processing: one is to skeletonize it using the Zhang–Suen thinning algorithm and the other is to identify the buds and obtain the center coordinates of the buds using the target-detection method YOLOv5; finally, combining with the depth information of the depth image, we use the coordinates of the buds to determine the location of the pruning point located on the skeleton image. The results show that PSP-net has better results in segmentation performance with mIoU reaching 83.73%. YOLOv5 performs better in target detection with mAP reaching 81.06% and F1 reaching 0.80. The accuracy of this method in determining the location of pruning points reaches 82.35%. It can provide a method for fruit tree pruning robots to determine the location of pruning points.

Bisimplicial separators

AbstractA minimal separator of a graph is a set such that there exist vertices with the property that separates from in , but no proper subset of does. For an integer , we say that a minimal separator is ‐simplicial if it can be covered by cliques and denote by the class of all graphs in which each minimal separator is ‐simplicial. We show that for each , the class is closed under induced minors, and we use this to show that the Maximum Weight Stable Set problem can be solved in polynomial time for . We also give a complete list of minimal forbidden induced minors for . Next, we show that, for , every nonnull graph in has a ‐simplicial vertex, that is, a vertex whose neighborhood is a union of cliques; we deduce that the Maximum Weight Clique problem can be solved in polynomial time for graphs in . Further, we show that, for , it is NP‐hard to recognize graphs in ; the time complexity of recognizing graphs in is unknown. We also show that the Maximum Clique problem is NP‐hard for graphs in . Finally, we prove a decomposition theorem for diamond‐free graphs in (where the diamond is the graph obtained from by deleting one edge), and we use this theorem to obtain polynomial‐time algorithms for the Vertex Coloring and recognition problems for diamond‐free graphs in , and improved running times for the Maximum Weight Clique and Maximum Weight Stable Set problems for this class of graphs.

Bipartite (P6,C6)-Free Graphs: Recognition and Optimization Problems

The canonical decomposition of a bipartite graph is a new decomposition method that involves three operators: parallel, series, and K⨁ S. The class of weak-bisplit graphs is the class of totally decomposable graphs with respect to these operators, and the class of bicographs is the class of totally decomposable graphs with respect to parallel and series operators. We prove in this paper that the class of bipartite (P6,C6)-free graphs is the class of bipartite graphs that are totally decomposable with respect to parallel and K⨁S operators. We present a linear time recognition algorithm for (P6,C6)-free graphs that is symmetrical to the linear recognition algorithms of weak-bisplit graphs and star1,2,3-free bipartite graphs. As a result of this algorithm, we present efficient solutions in this class of graphs for two optimization graph problems: the maximum balanced biclique problem and the maximum independent set problem.

QR Code Recognition Based on Image Processing

To solve the QR code recognition problem caused by ordinary camera collection, the recognition algorithm based on image processing is put forward in this paper. The whole process including image binarization, image tilt correction, image orientation, image geometric correction and image normalization allows images collected on different illumination conditions. Experiments show that the improved method can enhance the recognition speed of two-dimensional code and accuracy. QR i.e. “Quick Response” code is a 2D matrix code that is designed by keeping two points under consideration, i.e. it must store large amount of data as compared to 1D barcodes and it must be decoded at high speed using any handheld device like phones. QR code provides high data storage capacity, fast scanning, omnidirectional readability, and many other advantages including, error-correction (so that damaged code can also be read successfully) and different type of versions. Different varieties of QR code symbols like logo QR code, encrypted QR code, QR Code are also available so that user can choose among them according to their need. Now these days, a QR code is applied in different application streams related to marketing, security, academics etc. and gain popularity at a really high pace. Day by day more people are getting aware of this technology and use it accordingly. The popularity of QR code grows rapidly with the growth of smartphone users and thus the QR code is rapidly arriving at high levels of acceptance worldwide.

Recognition and optimisation method of impact deformation patterns based on point cloud and deep clustering: Applied to thin-walled tubes

The recognition and clustering of deformation modes are key to constructing impact deformation constraints for thin-walled structures. This paper transforms the clustering and recognition problem of structural impact deformation modes into a problem of clustering and recognition of point cloud sequences based on pseudo-labels. The effectiveness of the method is assessed, and the experimental results show that the accuracy of the proposed method can reach up to 92.17 % when using a pre-training deep neural network feature extractor, which is not only close to the 98.50 % accuracy of supervised learning classification models but also has a 16.84 % improvement in accuracy compared to the deep clustering method based on K-Means. Under different clustering conditions, the proposed method can effectively classify and recognise samples with similar deformation modes and has the ability to summarise and induce new deformation modes when the number of clusters exceeds the number of manual labels. Furthermore, this paper presents a multi-objective optimisation method for structural crashworthiness under impact deformation constraints based on the NSGA-II algorithm. This method constructs impact deformation constraints using surrogate models and deformation clustering and recognition models. The experimental results show that the proposed method can effectively constrain the generation of the population. It is found that there are a large number of Pareto solutions that do not belong to the expected impact deformation mode under the condition of no deformation mode constraint. In contrast, almost all the obtained Pareto solutions conform to the expected impact deformation mode under the condition of deformation mode constraint. In summary, under the condition of impact deformation constraint, the obtained Pareto solutions can satisfy the crashworthiness requirements while conforming to the expected impact deformation mode.

GNDAN: Graph Navigated Dual Attention Network for Zero-Shot Learning.

Zero-shot learning (ZSL) tackles the unseen class recognition problem by transferring semantic knowledge from seen classes to unseen ones. Typically, to guarantee desirable knowledge transfer, a direct embedding is adopted for associating the visual and semantic domains in ZSL. However, most existing ZSL methods focus on learning the embedding from implicit global features or image regions to the semantic space. Thus, they fail to: 1) exploit the appearance relationship priors between various local regions in a single image, which corresponds to the semantic information and 2) learn cooperative global and local features jointly for discriminative feature representations. In this article, we propose the novel graph navigated dual attention network (GNDAN) for ZSL to address these drawbacks. GNDAN employs a region-guided attention network (RAN) and a region-guided graph attention network (RGAT) to jointly learn a discriminative local embedding and incorporate global context for exploiting explicit global embeddings under the guidance of a graph. Specifically, RAN uses soft spatial attention to discover discriminative regions for generating local embeddings. Meanwhile, RGAT employs an attribute-based attention to obtain attribute-based region features, where each attribute focuses on the most relevant image regions. Motivated by the graph neural network (GNN), which is beneficial for structural relationship representations, RGAT further leverages a graph attention network to exploit the relationships between the attribute-based region features for explicit global embedding representations. Based on the self-calibration mechanism, the joint visual embedding learned is matched with the semantic embedding to form the final prediction. Extensive experiments on three benchmark datasets demonstrate that the proposed GNDAN achieves superior performances to the state-of-the-art methods. Our code and trained models are available at https://github.com/shiming-chen/GNDAN.

Open-set learning context recognizing in mobile learning: Problem and methodology

Mobile learning allows for an interactive way of learning through devices like smartphones. However, current methods usually rely on pre-set situations and struggle to recognize new contexts when they come up during testing. To solve this, we suggest the Open-set Learning Context Recognition Model (OLCRM). This model uses data extracted from smartphone sensors to identify whether a learning context is known or unknown. It also uses a Dual Discriminator Generative Adversarial Network (DDGAN) to create high-quality fake examples, which helps improve the accuracy of recognizing contexts. Experimental results demonstrate the effectiveness of OLCRM in open-set learning context recognition problems.

Human Scream Detection and Analysis for Controlling Crime Rate using Machine Learning and Deep Learning

Abstract: This paper addresses the problem of automatic detection and recognition of impulsive sounds, such as glass breaks, human screams, gunshots, explosions or door slams. A complete detection and recognition system is described and evaluated on a sound database containing more than 800 signals distributed among six different classes. Emphasis is set on robust techniques, allowing the use of this system in a noisy environment. The detection algorithm, based on a median filter, features a highly ro- bust performance even under important background noise conditions. In the recognition stage, two statistical classifiers are compared, using Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM), respec- tively. It can be shown that a rather good recognition rate (98% at 70dB and above 80% for 0dB signal-to-noise ratios) can be reached, even under severe gaussian white noise degradations.

Deep Learning-Based Dzongkha Handwritten Digit Classification

In computer vision applications, pattern recognition is one of the important fields in artificial intelligence. With the advancement in deep learning technology, many machine learning algorithms were developed to tackle the problem of pattern recognition. The purpose of conducting the research is to create the first-ever Dzongkha handwritten digit dataset and develop a model to classify the digit. In the study, the 3 layer set of CONV → ReLU → POOL, followed by a fully connected layer, dropout layer, and softmax function were used to train the digit. In the dataset, each class (0-9) contains 1500 images which are split into train, validation, and test sets: 70:20:10. The model was trained on three different image dimensions: 28 by 28, 32 by 32, and 64 by 64. Compared to image dimensions 28 by 28 and 32 by 32, 64 by 64 gave the highest train, validation, and test accuracy of 98.66%, 98.9%, and 99.13% respectively. In the future, the sample of digits needs to be increased and use the transfer learning concept to train the model.

Operations and Similarity Measures Between (m,n)-Fuzzy Sets

Recently Jun and Hur proposed (m, n)-fuzzy sets which can handle vagueness and uncertainty in information very efficiently in the process of solving complex problems. They defined basic operations over (m, n)-fuzzy sets. The present paper created some new operations over this super class of fuzzy sets and established many theorems related to the their properties. Further some distance and similarity measures of (m, n)-fuzzy sets are proposed and their properties are examined. Moreover, the proposed similarity measures are applied to the problem of pattern recognition.

A Fast Adaptive Millimeter-Wave Radar Clustering Algorithm

This paper focuses on the intelligent recognition problem of radar detection targets. Aiming at the low accuracy and slow speed of millimeter-wave radar clustering point cloud information, a feature algorithm of millimeter-wave radar suitable for detecting targets is proposed. In the detection of targets by millimeter-wave radar, distance is the biggest factor affecting the number and degree of sparsity. A method that combines the feature information of the point cloud with the KD tree proximity search algorithm and the DBSCAN clustering algorithm is proposed, which can adapt to the problems of uneven target point cloud, small amount of data and slow clustering speed. The improved algorithm can use the KD tree to quickly find adjacent points and calculate the distance between adjacent points. The corresponding number of thresholds is set according to the distance where the target is located, and the radius of the target area reflected by the millimeter-wave radar plus the distance of the last threshold point is used as the neighborhood radius of the improved algorithm. Therefore, fast and adaptive parameter adjustment of the millimeter-wave radar can be realized. Simulation tests show that the improved clustering algorithm has better parameters. The accuracy of the improved algorithm is increased by 4.2%, and it also greatly improves the clustering speed.

Forecasting Maximum Water Level Data for Post Sangkuliman using An Artificial Neural Network Backpropagation Algorithm

Neural Network (NN) is an information processing system that has characteristics similar to biological neural networks. One of the algorithms in NN is Backpropagation Neural Network (BPNN). BPNN is an excellent method for dealing with complex pattern recognition problems. In this research, maximum water level forecasting was carried out at Sangkuliman Post using a Backpropagation Neural Network. This research aims to obtain modeling for forecasting maximum water level, as well as forecasting results using the best model. The research results show that the best model is five neurons in hidden layer 1 and 3 neurons in hidden layer 2 with the backpropagation algorithm, the activation function used is binary sigmoid, the learning rate is 0.001, and the maximum iteration is 10,000,000 with the smallest RMSE result being 1.816. The forecast results for the following 12 periods are 1.672, 1.779, 1.523, 1.271, 1.752, 1.692, 1.335, 1.479, 1.750, 1.779, 1.340, 1.269, and 1.754. Forecasting results can be used by various parties in decision-making and planning in multiple fields, as an example to see the patterns of biological and vegetable life around Sangkuliman Post. Based of forecasting results, certain months show an increase in maximum water levels.

MI-OPTNET: AN OPTIMIZED DEEP LEARNING FRAMEWORK FOR MYOCARDIAL INFARCTION DETECTION

The conventional means of myocardial infarction (MI) detection using a 12-lead electrocardiogram (ECG) system include a pretrained network and machine learning interpretation of the complex ECG signals. They are computationally inefficient and demand high-performance hardware. Here, for the first time, we introduce an effective framework (MI-OptNet) using the particle swarm optimization model (PSO) in the design of a lightweight hybrid network combining convolutional neural network (CNN)-long short terms memory (LSTM) for MI and normal ECG detection. We optimized important design and training parameters based on limb leads’ signals and identified leads III and VI as the best ECG leads for the task based on their high classification performance ranging between 80 – 90 %, suggesting that they may provide more information about MI than the others. The other strategy of fusing the scores from all models at the decision level achieved the best result with a 10 % increase in the evaluated metrics. Our findings support the flexibility and adaptability of our framework for the design process using minimal computer efforts. We concluded that this approach may be used for other classification problems to assist engineers and designers in efficient decision-making and to solve complex signal classification and recognition problems.

Detecting and locating chemical intrusion in water distribution systems using 911 calls

ABSTRACT Intentional or unintentional chemical contamination of water distribution systems (WDSs) could have severe health and socio-economic consequences. High potency chemicals constituting, in essence, “super poisons” have the potential to be used in such intrusion scenarios. Some of these contaminants are capable of killing the victim in less than 1 h. Due to their high toxicity levels and short time from exposure to onset of symptoms, 911 call centers are likely the first point of contact for victims or their families with the authorities. Information such as 911 calls could be used to identify the ongoing event and potential intrusion locations. In this way, such emergency calls could function as an intrusion warning system. This study employs network hydraulic modelling to synthesize the 911 call patterns in the aftermath of such events. It then defines the scenarios as a multi-label pattern recognition problem. The synthesized data then was used to train a Convolutional Neural Network (CNN). The trained AI was applied to a real-world WDS with approximately 4000 km of pipe and 26,000 demand nodes. The results indicated that CNN is capable of accurately recognizing the pattern and pinpointing the originating location of the intrusion with an accuracy greater than 93%.

Extending Partial Representations of Circle Graphs in Near-Linear Time

The partial representation extension problem generalizes the recognition problem for geometric intersection graphs. The input consists of a graph G, a subgraph H⊆G\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$H \\subseteq G$$\\end{document} and a representation R′\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal R'$$\\end{document} of H. The question is whether G admits a representation R\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal R$$\\end{document} whose restriction to H is R′\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal R'$$\\end{document}. We study this question for circle graphs, which are intersection graphs of chords of a circle. Their representations are called chord diagrams. We show that for a graph with n vertices and m edges the partial representation extension problem can be solved in O((n+m)α(n+m))\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O((n + m) \\alpha (n + m))$$\\end{document} time, thereby improving over an O(n3)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(n^3)$$\\end{document}-time algorithm by Chaplick et al. (J Graph Theory 91(4), 365–394, 2019). The main technical contributions are a canonical way of orienting chord diagrams and a novel compact representation of the set of all canonically oriented chord diagrams that represent a given circle graph G, which is of independent interest.

SAT-Based Algorithms for Regular Graph Pattern Matching

Graph matching is a fundamental problem in pattern recognition, with many applications such as software analysis and computational biology. One well-known type of graph matching problem is graph isomorphism, which consists of deciding if two graphs are identical. Despite its usefulness, the properties that one may check using graph isomorphism are rather limited, since it only allows strict equality checks between two graphs. For example, it does not allow one to check complex structural properties such as if the target graph is an arbitrary length sequence followed by an arbitrary size loop. We propose a generalization of graph isomorphism that allows one to check such properties through a declarative specification. This specification is given in the form of a Regular Graph Pattern (ReGaP), a special type of graph, inspired by regular expressions, that may contain wildcard nodes that represent arbitrary structures such as variable-sized sequences or subgraphs. We propose a SAT-based algorithm for checking if a target graph matches a given ReGaP. We also propose a preprocessing technique for improving the performance of the algorithm and evaluate it through an extensive experimental evaluation on benchmarks from the CodeSearchNet dataset.

Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data

Learning from open-world noisy data, where both closed-set and open-set noise co-exist in the dataset, is a realistic but underexplored setting. Only recently, several efforts have been initialized to tackle this problem. However, these works assume the classes are balanced when dealing with open-world noisy data. This assumption often violates the nature of real-world large-scale datasets, where the label distributions are generally long-tailed, i.e. class-imbalanced. In this paper, we study the problem of robust visual recognition with class-imbalanced open-world noisy data. We propose a probabilistic graphical model-based approach: iMRF to achieve label noise correction that is robust to class imbalance via an efficient iterative inference of a Markov Random Field (MRF) in each training mini-batch. Furthermore, we design an agreement-based thresholding strategy to adaptively collect clean samples from all classes that includes corrected closed-set noisy samples while rejecting open-set noisy samples. We also introduce a noise-aware balanced cross-entropy loss to explicitly eliminate the bias caused by class-imbalanced data. Extensive experiments on several benchmark datasets including synthetic and real-world noisy datasets demonstrate the superior performance robustness of our method over existing methods. Our code is available at https://github.com/Na-Z/LIOND.

Analisis 5 (Lima) Tahapan Proses Keputusan Pembelian Terhadap Pengambilan Keputusan Mahasiswa Universitas 45 Surabaya Dalam Memilih Perguruan Tinggi

This research aims to find out and understand how University 45 Surabaya students make decisions in choosing a university which is analyzed through 5 (five) stages of the purchasing decision process, namely Problem Recognition, Information Search, Evaluation of Alternatives, Purchase Decision, and Postpurchase Behavior. The population in this study were all active students in the 2014-2016 academic year at University 45 Surabaya. Determining the sample for this study used probability sampling with proportional sample strata. The type of research is qualitative research. The analytical tool used is a descriptive statistical method through calculating the size of central tendency by looking for the average value (mean) at the Problem Recognition, Information Search, Evaluation of Alternatives, Purchase Decision stages, and the IPA (Importance-Performance Analysis) method for the Postpurchase Behavior stage which is used to rank various elements of service quality through the aspects of Expectation (expectations) and Performance (performance). Research results in stage I Problem Recognition (Problem Recognition), there is a total score of 371 with an average value of 74.20 and the lowest namely 322 with an average value of 64.40. where the total average is 712.40. At the Information Search stage, the highest total score was obtained, namely 378 with an average value of 75.60 and the lowest total score was 244 with an average value of 48.80, where the total average was 679.00. At the Evaluation of Alternatives stage, the highest total score was obtained, namely 378 with an average value of 75.60 and the lowest total score was 241 with an average value of 48.20, where the total average was 661.00. At the Purchase Decision stage, the highest total score was obtained, namely 369 with an average value of 73.80 and the lowest total score was 262 with an average value of 52.40, where the total average was 812.60.

Simulation modeling of the system of managing the psychophysiological state of a person based on non-verbal extralinguistic characteristics

Today, when artificial intelligence systems are being created, the time of constant dia-logue between humans and computer, there is a great demand for intelligent control systems and human-machine systems. These systems are very complex and require analysis and re-search. The publication is devoted to the simulation computer modeling of control of the psy-chological and physical state of a person. The basis of the human-computer dialogue system is the speech-to-text conversion sys-tem. The use of this system is the basis for the creation of computer language control systems. Unlike systems that work on the principle of identifying a single user response to a request and a proposal or a question from a password database, it is necessary to expand the lan-guage interface of the computer. It is necessary for the computer to accept commands from the operator and execute them only if the voice and its timbre match those registered in the database. Such a system will allow you to differentiate access to the computer and ensure se-curity for the user, preserve his privacy or save his personal data. After analyzing the speech activity of the operator, it became clear that it was necessary to develop a system of command control and «speech-to-text» conversion in the fused speech stream. This task is solved by comparing the words of the commands and is part of the problem of automatic recognition and understanding of the operator's human language. On the basis of such systems, a computer language control system can be created. The analysis has shown that unlike text-dependent identification systems, systems with a dialog method implement not only a one-time operator response to a query or question from the password database, but also the extension of its full-fledged language interface. The computer receives commands from the operator and executes them only if the voice matches the one registered in the database. This analysis is effective in the context of real-life speech activity of the operator. The literature review showed that for the development of sys-tems of command control and "speech-to-text" transformation in a stream of fused speech, it is necessary to use "mechanisms" of automatic recognition and understanding of the opera-tor's language.

Deep Learning and Image data-based surface cracks recognition of laser nitrided Titanium alloy

Laser nitriding, a high-precision surface modification process, enhances the hardness, wear resistance and corrosion resistance of the materials. However, laser nitriding process is prone to appearance of cracks when the process is performed at high laser energy levels. Traditional techniques to detect the cracks are time consuming, costly and lack standardization. Thus, this research aims to put forth deep learning-based crack recognition for the laser nitriding of Ti–6Al–4V alloy. The process of laser nitriding has been performed by varying duty cycles, and other process parameters. The laser nitrided sample has then been processed through optical 3D surface measurements (Alicona Infinite Focus G5), creating high resolution images. The images were then pre-processed which included 2D conversion, patchification, image augmentation and subsequent removal of anomalies. After preprocessing, the investigation focused on employing robust binary classification method based on CNN models and its variants, including ResNet-50, VGG-19, VGG-16, GoogLeNet (Inception V3), and DenseNet-121, to recognize surface cracks. The performance of these models has been optimized by fine tuning different hyper parameters and it is found that CNN base model along with models having less trainable parameters like VGG-19, VGG-16 exhibit better performance with accuracy of more than 98% to recognize cracks. Through the achieved results, it is found that VGG-19 is the most preferable model for this crack recognition problem to effectively recognize the surface cracks on laser nitrided Ti–6Al–4V material, owing to its best accuracy and lesser parameters compared to complex models like ResNet-50 and Inception-V3.