Search

The Picture Fuzzy Set (PFS) is a broadening of the fuzzy set and intuitionistic fuzzy set. Pattern recognition, picture segmentation, and decision-making are some of the applications of PFS. The dissimilarity measure technique is used to illustrate a decision-making issue on an image fuzzy set in this article. Decision-making is a technique that enables a computer to think like a person, and it is critical for machine learning and the application of artificial intelligence to machines. These aids robots in thinking like humans. Finally, the suggested approach is presented in this article using a case study based on a survey of 100 consumers performed at a two-wheeler showroom.

Banks and financial institutions use systematic business transaction fraud, individual analytics. Distrust analysis definition is based on a customer history of abnormal behaviors that indicate normal activities and fraud, manipulation or application analysis. The challenge of facing the banking and finance sector is in the form of fraudulent transactions. Combined with the explosive development of data and information, it has urged great advances in technology and communication, global consumer awareness, and capabilities. A comprehensive customer engagement strategy of the banking sector should establish opportunities through dynamic consumer estimation. Security is therefore essential for all banks to implement fraud detection methods to minimize their losses. The regulatory sequence based on different methods of machine learning has evolved to detect various fraudulent transactions. The effective way to detect the fraud detection mechanism is far more essential than the standard classification technology. Pattern Recognition K-Nearest Neighbor [PR-KNN] is developed for such a progressive search and non-parametric technique that evaluates the pseudo-nature to find the best solution to the problem. Regression and classification problems of fraudulent transactions mean the spending is reducing the number of false alarms. The detection systems are placed in bank fraud or fraudulent transactions after the transaction are expected to expectation.

Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures. However, due to the non-differentiable nature of spiking neuronal functions, the standard error back-propagation algorithm is not directly applicable to SNNs. In this work, we propose a tandem learning framework, that consists of an SNN and an Artificial Neural Network (ANN) coupled through weight sharing. The ANN is an auxiliary structure that facilitates the error back-propagation for the training of the SNN at the spike-train level. To this end, we consider the spike count as the discrete neural representation in the SNN, and design ANN neuronal activation function that can effectively approximate the spike count of the coupled SNN. The proposed tandem learning rule demonstrates competitive pattern recognition and regression capabilities on both the conventional frame-based and event-based vision datasets, with at least an order of magnitude reduced inference time and total synaptic operations over other state-of-the-art SNN implementations. Therefore, the proposed tandem learning rule offers a novel solution to training efficient, low latency, and high accuracy deep SNNs with low computing resources.

Hydraulic systems are a class of typical complex nonlinear systems, which have been widely used in manufacturing, metallurgy, energy, and other industries. Nowadays, the intelligent fault diagnosis problem of hydraulic systems has received increasing attention for it can increase operational safety and reliability, reduce maintenance cost, and improve productivity. However, because of the high nonlinear and strong fault concealment, the fault diagnosis of hydraulic systems is still a challenging task. Besides, the data samples collected from the hydraulic system are always in different sampling rates, and the coupling relationship between the components brings difficulties to accurate data acquisition. To solve the above issues, a deep learning model with multirate data samples is proposed in this article, which can extract features from the multirate sampling data automatically without expertise, thus it is more suitable in the industrial situation. Experiment results demonstrate that the proposed method achieves high diagnostic and fault pattern recognition accuracy even when the imbalance degree of sample data is as large as 1:100. Moreover, the proposed method can increase about 10% diagnosis accuracy when compared with some state-of-the-art methods.

Machine vision based planar grasping detection is challenging due to uncertainty about object shape, pose, size, etc. Previous methods mostly focus on predicting discrete gripper configurations, and may miss some ground-truth grasp postures. In this paper, a pixel-level grasp detection method is proposed, which uses deep neural network to predict pixel-level gripper configurations on RGB images. Firstly, a novel Oriented Arrow Representation model (OAR-model) is introduced to represent the gripper configuration of parallel-jaw and three-fingered gripper, which can partly improve the applicability to different grippers. Then, the Adaptive Grasping Attribute model (AGA-model) is proposed to adaptively represent the grasping attribute of objects, for resolving angle conflicts in training and simplifying pixel-level labeling. Lastly, the Adaptive Feature Fusion and Grasp Aware Network (AFFGA-Net) is proposed to predict pixel-level OAR-models on RGB images. AFFGA-Net improves the robustness in unstructured scenarios by using Hybrid Atrous Spatial Pyramid and Adaptive Decoder connected in sequence. On the public Cornell dataset and actual objects, our structure achieves 99.09\% and 98.0\% grasp detection accuracy respectively. In over 2,400 robotic grasp trials, our structure achieves average success rate of 98.77\% in single-object scenarios and 93.69\% in cluttered scenarios. Moreover, AFFGA-Net completes a grasp detection pipeline within 15 ms.

The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct properties, such as interpretability, simplicity, and hardware-friendliness. Although numerous empirical evaluations report on its performance, the mathematical analysis of its convergence is still open. In this article, we analyze the convergence of the TM with only one clause involved for classification. More specifically, we examine two basic logical operators, namely, the "IDENTITY"- and "NOT" operators. Our analysis reveals that the TM, with just one clause, can converge correctly to the intended logical operator, learning from training data over an infinite time horizon. Besides, it can capture arbitrarily rare patterns and select the most accurate one when two candidate patterns are incompatible, by configuring a granularity parameter. The analysis of the convergence of the two basic operators lays the foundation for analyzing other logical operators. These analyses altogether, from a mathematical perspective, provide new insights on why TMs have obtained state-of-the-art performance on several pattern recognition problems., Comment: 23 pages, 10 figures

Feature selection is a basic task for pattern recognition and classification. It enhances the performance of the classification algorithms with the help of removing the redundant features. Thanks to eliminating irrelevant features, the computational time is decreased. Thus, intensive works have been carried out in this area. This paper proposes a new standard error-based artificial bee colony (SEABC) algorithm for the feature selection problem, which is developed by integrating standard error-based new solution search mechanisms into the original artificial bee colony algorithm. The SEABC algorithm is used for feature selection. Shannon entropy function is used to serve as the objective function of the SEABC algorithm. Thirteen datasets are used from UCI machine learning datasets. Features are selected according to Shannon conditional entropy values and then a threshold process is implemented to find their best relevant subset. Support Vector Machines (SVMs) and k-Nearest Neighbor (KNN) are used as the optimal classifiers. The proposed SEABC algorithm is compared with genetic algorithm (GA), particle swarm optimization (PSO), ABC, improved ABC (I-ABC), Gbest-guided ABC (GABC), and PS-ABC algorithms. In general, it is observed that the SEABC algorithm achieves better classification results than other well-known algorithms.

Decision tree is a widely used non-parametric technique in machine learning, data mining and pattern recognition. It is simple to understand and interpret, however it faces challenges such as handling higher dimensional and class imbalanced datasets, over-fitting and instability. To overcome some of these issues, vertical partitioning approaches like serial partitioning, theme based partitioning are used in the literature. A vertical partitioning approach divides the feature set into subsets of features (blocks) and makes use of these subsets for subsequent tasks. In this work, we use the ideas of music rhythm tree to propose a novel vertical partitioning technique. It orders the features based on the average correlation strength of the features before partitioning the feature set. The proposed method is proved to be superior by showing an average of 13.8 % , 6 % , 9.8 % , 19.7 % , 9.4 % , and 29.4 % higher classification accuracy over C4.5, Random Forest, Bagging, Adaboost, an ensemble technique and a vertical partitioning technique respectively. Our empirical results on 15 datasets demonstrate that the proposed vertical partitioning method is more stable and better in handling class-imbalanced data. Finally, some popular statistical tests are conducted to validate the statistical significance of the results of the proposed method.

In vehicle operation, in order to maximize the fuel economy, the propulsion system control can easily adapt to pressure and temperature variations as these variations can be measured by sensors. However, it is challenging to detect driving cycles. With growing progress made in the artificial intelligence field, pattern recognition gains momentum in various applications. This study presents a study on driving cycle pattern recognition based on supervised learning. Training data 2-D visualization is achieved by t-SNE algorithm. Ten out of twelve supervised learning algorithms predict driving conditions with the accuracy at 88% or higher and Extra Tree algorithm leads the recognition accuracy at 90.26%. To improve recognition accuracy, two hierarchical frameworks are proposed by integrating multiple supervised learning methods using weighted average and vote methods. The two hierarchical frameworks boost the driving condition recognition accuracy from 90.26% to 90.43% (weighted average) and 91.76% (vote). The results are further validated in holdout test. Additionally, a plug-in hybrid electric vehicle simulation shows 3.88%-5.82% fuel economy improvement when compared to baseline method. Two hierarchical methods outperform the Extra Tree method by 2% fuel economy. In summary, supervised learning shows great potential to detect driving cycles for vehicle energy saving.

The interest on graph matching has not stopped growing since the late seventies. The basic idea of graph matching consists of generating graph representations of different data or structures and compare those representations by searching correspondences between them. There are manifold techniques that have been developed to find those correspondences and the choice of one or another depends on the characteristics of the application of interest. These applications range from pattern recognition (e.g. biometric identification) to signal processing or artificial intelligence. One of the aspects that make graph matching so attractive is its ability to facilitate data analysis, and medical imaging is one of the fields that can benefit from this in a greater extent. The potential of graph matching to find similarities and differences between data acquired at different points in time shows its potential to improve diagnosis, follow-up of human diseases or any other of the clinical scenarios that require comparison between different datasets. In spite of the large amount of papers that were published in this field to the date there is no survey paper of graph matching for clinical applications. This survey aims to fill this gap.

In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as document image classification and document retrieval. As many document types have a distinct visual style, learning only visual features with deep CNNs to classify document images have encountered the problem of low inter-class discrimination, and high intra-class structural variations between its categories. In parallel, text-level understanding jointly learned with the corresponding visual properties within a given document image has considerably improved the classification performance in terms of accuracy. In this paper, we design a self-attention-based fusion module that serves as a block in our ensemble trainable network. It allows to simultaneously learn the discriminant features of image and text modalities throughout the training stage. Besides, we encourage mutual learning by transferring the positive knowledge between image and text modalities during the training stage. This constraint is realized by adding a truncated-Kullback-Leibler divergence loss Tr-KLD-Reg as a new regularization term, to the conventional supervised setting. To the best of our knowledge, this is the first time to leverage a mutual learning approach along with a self-attention-based fusion module to perform document image classification. The experimental results illustrate the effectiveness of our approach in terms of accuracy for the single-modal and multi-modal modalities. Thus, the proposed ensemble self-attention-based mutual learning model outperforms the state-of-the-art classification results based on the benchmark RVL-CDIP and Tobacco-3482 datasets., Accepted at IJDAR 2021

The recognition of online handwriting is a vital application of pattern recognition, which involves the extraction of spatial and temporal information of handwritten patterns, and understanding the handwritten text while writing on the digital surface. Although, online handwriting recognition is a mature but exciting and fast developing field of pattern recognition, the same is not true for many of the Indic scripts. Gurmukhi is one of such popular scripts of India, and online handwriting recognition issues for larger units as words or sentences largely remained unexplored for this script till date. The existing study and first ever attempt for online handwritten Gurmukhi word recognition has relied upon the widely used hidden Markov model. This existing study evaluated against and performed very well in their chosen metrics. But, the available online handwritten Gurmukhi word recognition system could not obtain more than 90% recognition accuracy in data dependent environment too. The present study provided benchmark results for online handwritten Gurmukhi word recognition using deep learning architecture convolutional neural network, and obtained above 97% recognition accuracy in data dependent mode of handwriting. The previous Gurmukhi word recognition system followed the stroke based class labeling approach, whereas the present study has followed the word based class labeling approach. Present Online handwritten Gurmukhi word recognition results are quite satisfactory. Moreover, the proposed architecture can be used to improve the benchmark results of online handwriting recognition of several major Indian scripts. Experimental results demonstrated that the deep learning system achieved great results in Gurmukhi script and outperforms existing results in the literature.

Fish classification (FC) is an expansively studied problem in the domains of image segmentation, pattern recognition, and information retrieval. It has been applied in a countless number of domains including target marketing. Meanwhile, governments are obliged to maintain the fish supply and balance between the ecosystem, commercial, agriculture field, marine scientists, and industrial arena of fish including the nutrition and canning factories. The various FC techniques performance is compared relying on the availability of preprocessing and feature extraction methods, the number of extracted features and classification accuracy, the number of fish families/species recognized. This survey also reviewed the use of Databases such as Fish4-Knowledge (F4K), knowledge database, and Global Information System (GIS) on Fishes and other FC databases. The study on preprocessing methods features extraction techniques and classifiers are gathered from recent works to enhance the understanding of the characteristics of preprocessing methods, features extraction techniques, and classifiers to guide future research directions and compensate for current research gaps.

One of the major reasons of death worldwide is Cardiovascular diseases. One of its type is Arrhythmia in which normal rhythm of heart is varied due to damage in heart muscles and electrolyte imbalance. To study cardiovascular disease, Electrocardiogram (ECG) signal is used that plays a significant role in identifying Arrhythmia. By using a combination of Multivariate Empirical Mode Decomposition (MEMD) and Artificial Neural Network (ANN), a hybrid technique is proposed in this research work to detect and classify Arrhythmia. MEMD, a promising technique that is used nowadays for denoising of multichannel signals, is used in this work. Two main features, i.e., RR interval and Heart Rate are extracted from the ECG signal for the detection of Arrhythmia. Using these features, Arrhythmia is classified into Tachycardia and Bradycardia. Classification is done using pattern recognition of ANN in which Multilayer feed forward neural network is used and trained through Back Propagation Algorithm. Results that are achieved using proposed technique is compared with previous existing techniques as in 2016 (Discrete Wavelet Transform) DWT and ANN gave 87.01% and in 2018 (Empirical Mode Decomposition) EMD and (Linear Discriminant Analysis) LDA gave 87% accuracy. As compare to these techniques, the proposed technique results show that it is an efficient technique that gives better accuracy of 89.8%.

Facial Attribute Classification (FAC) has attracted increasing attention in computer vision and pattern recognition. However, state-of-the-art FAC methods perform face detection/alignment and FAC independently. The inherent dependencies between these tasks are not fully exploited. In addition, most methods predict all facial attributes using the same CNN network architecture, which ignores the different learning complexities of facial attributes. To address the above problems, we propose a novel deep multi-task multi-label CNN, termed DMM-CNN, for effective FAC. Specifically, DMM-CNN jointly optimizes two closely-related tasks (i.e., facial landmark detection and FAC) to improve the performance of FAC by taking advantage of multi-task learning. To deal with the diverse learning complexities of facial attributes, we divide the attributes into two groups: objective attributes and subjective attributes. Two different network architectures are respectively designed to extract features for two groups of attributes, and a novel dynamic weighting scheme is proposed to automatically assign the loss weight to each facial attribute during training. Furthermore, an adaptive thresholding strategy is developed to effectively alleviate the problem of class imbalance for multi-label learning. Experimental results on the challenging CelebA and LFWA datasets show the superiority of the proposed DMM-CNN method compared with several state-of-the-art FAC methods.

A highly precise and timely diagnosis technology can help effectively monitor and adjust the sucker rod production system (SRPS) used in oil wells to ensure a safe and efficient production. The current diagnosis method is pattern recognition of a dynamometer card (DC) based on feature extraction and perceptron. The premise of this method is that the training and target data have the same distribution. However, the training data are collected from a field SRPS with different system parameters designed to adapt to production conditions, which may significantly affect the diagnostic accuracy. To address this issue, in this study, an improved model of the sucker rod string (SRS) is derived by adding fault-parameter dimensions, with which DCs under 16 working conditions could be generated. Subsequently an adaptive diagnosis method is proposed by taking simulated DCs generated near the working point of the target SRPS as training data. Meanwhile, to further improve the accuracy of the proposed method, the DC features are improved by relative normalization and using additional features of the DC position to increase the distance between different types of samples. The parameters of the perceptron are optimized to promote its discriminability. Finally, the accuracy and real-time performance of the proposed adaptive diagnosis method are validated using field data.

T-spherical fuzzy set (TSFS) is a generalized version of the spherical fuzzy set (SFS) and picture fuzzy set (PFS) to manage awkward and unpredictable information in realistic decision issues. TSFS deals with yes, abstinence, no, and refusal type of fuzzy information. This manuscript aims to observe the drawbacks of some existing dice similarity measures (DSMs) and to propose some new DSMs in the environment of TSFSs. The validation of the new DSMs is proved. The defined DSMs are further extended to introduce some generalized DSMs (GDSMs) and their special cases are studied. Additionally, the TOPSIS method using the entropy measures (EMs) based on TSFSs is also explored and verified with the help of some examples. The proposed new GDSMs and TOPSIS method are applied to the problem of building material recognition, medical diagnosis, clustering, and the results obtained are investigated. A comparison of the new theory is established where the advancement of the proposed DSMs is elaborated under some conditions. The advantages of the new DSMs and the drawbacks of the previous DSMs of IFSs, PyFSs, and PFSs have been studied because of their applicability. The article is comprehensively summarized, and some possible future directions are stated.

In computer-based search systems, similarity plays a key role in replicating the human search process. Indeed, the human search process underlies many natural abilities such as image recovery, language comprehension, decision making, or pattern recognition. The search for images consists of establishing a correspondence between the available image and that sought by the user, by measuring the similarity between the images. Image search by content is generaly based on the similarity of the visual characteristics of the images. The distance function used to evaluate the similarity between images depends notonly on the criteria of the search but also on the representation of the characteristics of the image. This is the main idea of a content-based image retrieval (CBIR) system. In this article, first, we constructed type-2 beta fuzzy membership of descriptor vectors to help manage inaccuracy and uncertainty of characteristics extracted the feature of images. Subsequently, the retrieved images are ranked according to the novel similarity measure, noted type-2 fuzzy nearness measure (IT2FNM). By analogy to Type-2 Fuzzy Logic and motivated by near sets theory, we advanced a new fuzzy similarity measure (FSM) noted interval type-2 fuzzy nearness measure (IT-2 FNM). Then, we proposed three new IT-2 FSMs and we have provided mathematical justification to demonstrate that the proposed FSMs satisfy proximity properties (i.e. reflexivity, transitivity, symmetry, and overlapping). Experimental results generated using three image databases showing consistent and significant results.

The pattern recognition of surface electromyography (sEMG) signal is an important application in the realization of human-machine interface. However, due to the disturbance of human body, sensors and environment, sEMG signal usually contains lots of noise, which brings great challenges to the high-accuracy sEMG pattern recognition. In addition, embedded human wearable devices are becoming more and more popular nowadays. How to realize the sEMG recognition method with low power consumption and high noise immunity has also become a difficult and very meaningful research topic. In this paper, a spiking neural network (SNN) classification method based on second-order information bottleneck training is proposed. Firstly, the training loss function for classification neural networks is constructed based on the proposed second-order information bottleneck. The method is used to train the conventional continuous-valued neural network and convert it into an SNN model with equivalent structure and connection weights. Then, the converted SNN is used to classify the sEMG signal patterns. Through a series of theoretical analysis and experimental results, it is proved that this method has significant advantages in terms of generalization of network determination and computational efficiency. The experimental code can be accessed from https://github.com/anvien/2OIB-for-sEMG-Recognition.

In recent years, researchers have made a great success on the automatic classification and detection of malware utilizing machine learning methods. However, most machine learning based approaches over rely on the training samples such that a new malware family not belonging to the training set cannot be identified. To address such issue, we propose a soft relevance value (s-value), a new evaluating way of feature soft relevance that uses the mixed distance criterion to assess classified results. Specifically, we leverage the mixed distance criterion from pattern recognition to distinguish testing samples as a new family which is not labeled in training set. Finally, we evaluate how s-value can be used to distinguish and classify a new malware family with the malware datasets from the Research Prediction Competition of Microsoft Malware Classification Challenge and Windows (Kaggle). The experimental results show that, the train-ing time is approximately 12 hours, while the prediction time is only ∼0.5 second. Comparing against the Kaggle winner, our time costs for training and pprediction only occupy 16.7% and 3.8% of the winner.s time costs, respectively. The accuracy of classifying malware reaches 99.8%. Such results indicates that our proposed s-value achieves a balance in accuracy, training and prediction time, and outperforms the state-of-the-art machine learning based malware detection approaches. Besides, our method is able to identify new malware families that are not included in the training set.

Feature selection is important in both machine learning and pattern recognition. Successfully selecting informative features can significantly increase learning accuracy and improve result comprehensibility. Various methods have been proposed to identify informative features from high-dimensional data by removing redundant and irrelevant features to improve classification accuracy. In this article, we systematically survey existing sparse learning models for feature selection from the perspectives of individual sparse feature selection and group sparse feature selection, and analyze the differences and connections among various sparse learning models. Promising research directions and topics on sparse learning models are analyzed.

This article investigates hardware implementation of hierarchical temporal memory (HTM), a brain-inspired machine learning algorithm that mimics the key functions of the neocortex and is applicable to many machine learning tasks. Spatial pooler (SP) is one of the main parts of HTM, designed to learn the spatial information and obtain the sparse distributed representations (SDRs) of input patterns. The other part is temporal memory (TM) which aims to learn the temporal information of inputs. The memristor, which is an appropriate synapse emulator for neuromorphic systems, can be used as the synapse in SP and TM circuits. In this article, a memristor-based SP (MSP) circuit structure is designed to accelerate the execution of the SP algorithm. The presented MSP has properties of modeling both the synaptic permanence and the synaptic connection state within a single synapse, and on-device and parallel learning. Simulation results of statistic metrics and classification tasks on several real-world datasets substantiate the validity of MSP.

Automatic face recognition system is suggested in this work on the basis of appearance based features focusing on the whole image as well as local based features focusing on critical face points like eyes, mouth, and nose for generating further details. Face detection is the major phase in face recognition systems, certain method for face detection (Viola-Jones) has the ability to process images efficiently and achieve high rates of detection in real time systems. Dimension reduction and feature extraction approaches are going to be utilized on the cropped image caused by detection. One of the simple, yet effective ways for extracting image features is the Local Binary Pattern Histogram (LBPH), while the technique of Principal Component Analysis (PCA) was majorly utilized in pattern recognition. Also, the technique of Linear Discriminant Analysis (LDA) utilized for overcoming PCA limitations was efficiently used in face recognition. Furthermore, classification is going to be utilized following the feature extraction. The utilized machine learning algorithms are PART and J48. The suggested system is showing high accuracy for detection with Viola-Jones 98.75, whereas the features which are extracted by means of LDA with J48 provided the best results of (F-measure, Recall, and Precision).

Background: Hand tremor is one of the consequences of MS disease degrading quality of patient’s life. Recently DBS is used as a prominent treatment to reduce this effect. Evaluation of this approach has significant importance because of the prevalence rate of disease.Objective: The purpose of this study was the nonlinear analysis of tremor signal in order to evaluate the quantitative effect of DBS on reducing MS tremor and differentiating between them using pattern recognition algorithms.Material and Methods:In this paper, nine features were extracted from the tremor signal. Through statistical analysis, the significance level of each feature was examined. Finally, tremor signals were categorized by SVM, weighted KNN and NN classifiers. The performance of methods was compared with an ROC graph.Results:The results have demonstrated that dominant frequency, maximum amplitude and energy of the first IMF, deviation of the direct path, sample entropy and fuzzy entropy have the potential to create a significant difference between the tremor signals. The classification accuracy rate of tremor signals in three groups for Weighted KNN, NN and SVM with Gaussian and Quadratic kernels resulted in 95.1%, 93.2%, 91.3% and 88.3%, respectively.conclusion: Generally, nonlinear and nonstationary analyses have a high potential for a quantitative and objective measure of MS tremor. Weighted KNN has shown the best performance of classification with the accuracy of more than 95%. It has been indicated that DBS has a positive influence on reducing the MS tremor. Therefore, DBS can be used in the objective improvement of tremor in MS patients.

Automatic modulation classification (AMC) is to identify the modulation type of a received signal, which plays a vital role to ensure the physical-layer security for Internet of Things (IoT) networks. Inspired by the great success of deep learning in pattern recognition, the convolutional neural network (CNN) and recurrent neural network (RNN) are introduced into the AMC. In general, there are two popular data formats used by AMC, which are in-phase/quadrature (I/Q) representation and amplitude/phase (A/P) representation, respectively. However, most of AMC algorithms aim at structure innovations, while the differences and characteristics of I/Q and A/P are ignored to analyze. In this paper, lots of popular AMC algorithms are reproduced and evaluated on the same dataset, where the I/Q and A/P are used respectively for comparison. Based on the experimental results, it is found that: (i) CNN-RNN-like algorithms using A/P as input data are superior to those using I/Q at high signal-noise-ratio (SNR), while it has an opposite result in low SNR; (ii) the features extracted from I/Q and A/P are complementary to each other. Motivated by the aforementioned findings, a multi-task learning based deep neural network (MLDNN) is proposed, which effectively fuses I/Q and A/P. In addition, the MLDNN also has a novel backbone, which is made up of three blocks to extract discriminative features, and they are CNN block, bidirectional gated recurrent unit (BiGRU) block and a step attention fusion network (SAFN) block. Different from most of CNN-RNN-like algorithms (i.e. they only use the last step outputs of RNN), all step outputs of BiGRU can be effectively utilized by MLDNN with the help of SAFN. Extensive simulations are conducted to verify that the proposed MLDNN achieves superior performance in the public benchmark.

Development of a pattern recognition system is comprised from a number of subtasks: formalization of the subject area, formation of a training sample, training of the recognition system, reduction of the dimensionality of the feature space, the problem of pattern recognition itself (based on the degree of similarity of the detected object with the training sample), recognition quality control, adaptation, inverse problem recognition, cluster and structural analysis, cognitive analysis. The article considers the formalization one of the subtasks (formation of the training sample). The conclusion about the "almost linear dependence" of the length of the training sequences and the dimensionality of the feature space is made using the proposed probabilistic model. Evaluation of the length of the training sequences for realistic values of model parameters is performed.

Artificial Neural Network (ANN) is a form of computation inspired by the arrangement and purpose of the brain. Pattern Recognition is one of the demanding areas under Artificial Neural Network and pattern association is one of the major tasks through which pattern recognition is realized. Nowadays researchers are taking interest in the combination of evolutionary algorithms and ANN. In the present work, an attempt is being made to analyze the performance of Hopfield Associative Memory with Monte Carlo adaptation rule and evolutionary searching (Genetic Algorithm) for pattern storage and recall. The training pattern set has been taken a set of five Greek alphabet letters as different objects. The aim is to store Patterns with MC adaptation rule and get the best weight matrices for efficient recalling of any given set patterns. The neural networks architectures have been taken up for storing the given set of inputs, for which conventional Hebbian and Monte Carlo adaptation rule is considered. During the mutation process, various mutation probabilities are supposed to be evaluated. The detailed simulated results thus obtained will be presented with the help of tables and graph.

Semantics and motion are two cues of essence for the success in video salient object detection. Most existing deep-learning based approaches extract semantic features by the use of only one fully convolutional network with simple stacked encoders. They simulate motion patterns of video objects with two consecutive frames being simultaneously fed into a convolutional LSTM network or a weights-sharing fully convolutional network. However, such approaches have the shortcomings of producing a coarse predicted saliency map or requiring significant computational overheads. In this paper, we present a novel approach with cascaded fully convolutional networks involving motion attention (abbreviated as CFCN-MA), to achieve real-time saliency detection in videos. Our key idea is to construct twofold fully convolutional networks in order to gain a saliency map from coarse to fine. We devise an optical flow-based motion attention mechanism to improve the prediction accuracy of the initial fully convolutional networks, using the popular FlowNet2-SD model that is efficient and effective for motion pattern recognition of distinctive objects in videos. This method can obtain a fine saliency map with a refined region of interest. Moreover, we propose a means for calculating attention-guided intersection-over-union loss (shortnamed as AIoU) to supervise the CFCN-MA model in learning a saliency map with both clear edge and complete structure. Our approach is evaluated on three popular benchmark datasets, namely DAVIS, ViSal and FBMS. Experimental results demonstrate that our method outperforms many state-of-the-art techniques while meeting the real-time demand at 27 fps.

This study presents an efficient sparse learning-based pattern recognition framework to recognize the discrete states of three emotions-happy, angry, and neutral emotion-using electroencephalogram (EEG) signals. In affective computing with massive spatiotemporal brainwave signals, a large number of features can be extracted to capture various information from multivariate brain data. However, it is often a challenge to model high-dimensional features efficiently in consideration of the intrinsic structure, such as channel location, feature group, time epoch, etc. In this study, features were extensively extracted from EEG signals and were applied on a structured sparse learning model to perform feature selection and classification simultaneously. An efficient ADMM-based algorithm with a closed-form solution was developed to solve the sparse group model. Experimental results show that the proposed method is capable of selecting a small number of important neural features to discriminate the three emotion states with high classification accuracy. With greatly enhanced interpretability and efficiency to learn neural signatures of brain activity from high-dimensional-feature, low-sample-size brain imaging data, the presented computational framework is promising for handling emotion recognition problems with high-dimensional brain imaging data.

The Internet of Things (IoT) is becoming an indispensable part of everyday life, enabling a variety of emerging services and applications. However, the presence of rogue IoT devices has exposed the IoT to untold risks with severe consequences. The first step in securing the IoT is detecting rogue IoT devices and identifying legitimate ones. Conventional approaches use cryptographic mechanisms to authenticate and verify legitimate devices’ identities. However, cryptographic protocols are not available in many systems. Meanwhile, these methods are less effective when legitimate devices can be exploited or encryption keys are disclosed. Therefore, non-cryptographic IoT device identification and rogue device detection become efficient solutions to secure existing systems and will provide additional protection to systems with cryptographic protocols. Non-cryptographic approaches require more effort and are not yet adequately investigated. In this paper, we provide a comprehensive survey on machine learning technologies for the identification of IoT devices along with the detection of compromised or falsified ones from the viewpoint of passive surveillance agents or network operators. We classify the IoT device identification and detection into four categories: device-specific pattern recognition, Deep Learning enabled device identification, unsupervised device identification, and abnormal device detection. Meanwhile, we discuss various ML-related enabling technologies for this purpose. These enabling technologies include learning algorithms, feature engineering on network traffic traces and wireless signals, incremental learning, and abnormality detection.

The Random Subspace Method (RSM) is an ensemble procedure in which each constituent learner is constructed using a randomly chosen subset of the data features. Regression trees are ideal candidate learners in RSM ensembles. By constructing trees upon different feature subsets, RSM reduces correlation between trees resulting in a stronger ensemble. Furthermore, it lessens computational burden by only considering a subset of the features when building each tree. Despite its apparent advantages, RSM has a notable drawback. In some instances a randomly chosen subspace may lack informative features. This is especially true in situations in which the number of truly informative variables is small relative to the total number of variables. Trees that are constructed using feature subsets lacking informative features can be damaging to the ensemble. Here we present Grafted Random Subspaces (GRS) and Vanishing Random Subspaces (VRS), two novel ensemble procedures designed to remedy the aforementioned drawback by reusing information across trees. Both techniques borrow from RSM by growing individual trees on randomly selected feature subsets. For each tree in a GRS ensemble, the most important variable is identified and guaranteed inclusion into the next q feature subsets. This allows GRS to recycle a promising feature from one tree across several successive trees, effectively grafting the variable into the next q active subsets. In the VRS procedure the least important feature is guaranteed exclusion from the next q feature subsets. This creates a more enriched pool of candidate variables from which the successive feature subsets are drawn.

Most scientific contributions addressing cyber-security issues in water distribution networks present proposals of detection systems and very few propose location systems. A novel methodology for detection and location of cyber-attacks in water distribution networks (WDNs) is proposed in this paper. Structural analysis and autoencoder neural networks are effectively combined with a the control chart Adaptive Exponentially Weighted Moving Average (AEWMA). In the training phase, the proposed detection and location framework only requires data from normal operating conditions and knowledge about the behavioral model of the system which represents an advantage over previous works that demand for additional data of cyber-attacks. Among other advantages of the proposed methodology are the high performance in the effective, robust and early detection and the effectiveness of the location strategy. The proposal was evaluated with the known case study BATADAL.

In this paper, we propose to exploit the side-tuning framework for multimodal document classification. Side-tuning is a methodology for network adaptation recently introduced to solve some of the problems related to previous approaches. Thanks to this technique it is actually possible to overcome model rigidity and catastrophic forgetting of transfer learning by fine-tuning. The proposed solution uses off-the-shelf deep learning architectures leveraging the side-tuning framework to combine a base model with a tandem of two side networks. We show that side-tuning can be successfully employed also when different data sources are considered, e.g. text and images in document classification. The experimental results show that this approach pushes further the limit for document classification accuracy with respect to the state of the art., Comment: 2020 25th International Conference on Pattern Recognition (ICPR)

Higher-order fuzzy decision-making methods have become powerful tools to support decision-makers in solving their problems effectively by reflecting uncertainty in calculations better than crisp sets in the last 3 decades. Fermatean fuzzy set proposed by Senapati and Yager, which can easily process uncertain information in decision making, pattern recognition, medical diagnosis et al., is extension of intuitionistic fuzzy set and Pythagorean fuzzy set by relaxing the restraint conditions of the support for degrees and support against degrees. In this paper, we focus on the similarity measures of Fermatean fuzzy sets. The definitions of the Fermatean fuzzy sets similarity measures and its weighted similarity measures on discrete and continuous universes are given in turn. Then, the basic properties of the presented similarity measures are discussed. Afterward, a decision-making process under the Fermatean fuzzy environment based on TOPSIS method is established, and a new method based on the proposed Fermatean fuzzy sets similarity measures is designed to solve the problems of medical diagnosis. Ultimately, an interpretative multi-criteria decision making example and two medical diagnosis examples are provided to demonstrate the viability and effectiveness of the proposed method. Through comparing the different methods in the multi-criteria decision making and the medical diagnosis application, it is found that the new method is as efficient as the other methods. These results illustrate that the proposed method is practical in dealing with the decision making problems and medical diagnosis problems.

In the milling process of metallic parts, appropriate tool conditions are essential to reducing processing faults and ensuring manufacturing quality. However, the existing condition monitoring methods are usually limited by recognizing intermediate abnormal states during milling processing, which is inefficient and impractical for real practical applications. Therefore, this paper proposes a tool condition monitoring (TCM) method in the milling process based on multisource pattern recognition and state transfer paths. First, the improved K-means clustering method is used to generate multiple patterns of tool wear. Second, a multisource pattern recognition model framework is developed, and multiple observation windows and the pattern transfer path are considered in the multisource pattern recognition model. Finally, PHM2010 datasets are used to verify the feasibility of the proposed method, and the results demonstrate the applicability of the proposed method in practice for tool condition monitoring.

The grading of gemstones is currently a manual procedure performed by gemologists. A popular approach uses reference stones, where those are visually inspected by specialists that decide which one of the available reference stone is the most similar to the inspected stone. This procedure is very subjective as different specialists may end up with different grading choices. This work proposes a complete framework that entails the image acquisition and goes up to the final stone categorization. The proposal is able to automate the entire process apart from including the stone in the created chamber for the image acquisition. It discards the subjective decisions made by specialists. This is the first work to propose a machine learning approach coupled with image processing techniques for emerald grading. The proposed framework achieves 98% of accuracy (correctly categorized stones), outperforming a deep learning approach. Furthermore, we also create and publish the used dataset that contains 192 images of emerald stones along with their extracted and pre-processed features.

How to represent and classify a testing sample for the representation-based classification (RBC) plays an important role in the filed of pattern recognition. As a typical kind of the representation-based classification with promising performance, collaborative representation-based classification (CRC) adopts all the training samples to collaboratively represent and then classify each testing sample with the reconstructive residuals among all the classes. However, most of the CRC methods fail to make full use of the localities and discrimination information of data in collaborative representation. To address this issue to further improve the classification performance, we design a novel supervised CRC method entitled locality-constrained weighted collaborative-competitive representation-based classification (LWCCRC). In the proposed method, the localities of data are taken into account by using the positive and negative nearest samples of each testing sample with their corresponding weighted constraints. Such devised locality-constrained weighted term can model the similarity and natural discrimination information contained in the neighborhood region for each testing sample to obtain the favorable representation. Moreover, a competitive constraint is introduced to enhance pattern discrimination among the categorical collaborative representations. To explore the effectiveness of our proposed LWCCRC, the extensive experiments are carried out on three different types of data sets. The experimental results demonstrate that the proposed LWCCRC significantly outperforms the recent state-of-the-art CRC methods.

Fine-grained classification is a challenging problem with small inter-class variance and large intra-class variance. It becomes more difficult when only a few labeled training samples are available. Inspired by the procedure of human recognition that two similar objects are usually distinguished by comparing their key parts, we develop a novel few-shot fine-grained classification method, which learns to model the inter-class boundaries in human-like style, i.e., extracting key-part structure information of objects and performing part-by-part comparison. To this end, we first extract the key parts of objects by using the designed key-part detector, which are then encoded by our structure encoder for the final comparison. To tackle with the scarce labeled samples, we train the proposed network under the metric-based few-shot learning methodology. Experiments on benchmark datasets demonstrate the effectiveness of the proposed method compared with the state-of-the-art counterparts. Besides, extensive investigations are conducted to verify the contributions of the key components of our method.

Deep convolutional neural networks (DCNNs) have dominated as the best performers on almost all computer vision tasks over the past several years. However, it remains a major challenge to deploy these powerful DCNNs in resource-limited environments, such as embedded devices and smartphones. To this end, 1-bit CNNs have emerged as a feasible solution as they are much more resource-efficient. Unfortunately, they often suffer from a significant performance drop compared to their full-precision counterparts. In this paper, we propose a novel Bayesian Optimized compact 1-bit CNNs (BONNs) model, which has the advantage of Bayesian learning, to improve the performance of 1-bit CNNs significantly. BONNs incorporate the prior distributions of full-precision kernels, features, and filters into a Bayesian framework to construct 1-bit CNNs in a comprehensive end-to-end manner. The proposed Bayesian learning algorithms are well-founded and used to optimize the network simultaneously in different kernels, features, and filters, which largely improves the compactness and capacity of 1-bit CNNs. We further introduce a new Bayesian learning-based pruning method for 1-bit CNNs, which significantly increases the model efficiency with very competitive performance. This enables our method to be used in a variety of practical scenarios. Extensive experiments on the ImageNet, CIFAR, and LFW datasets show that BONNs achieve the best in classification performance compared to a variety of state-of-the-art 1-bit CNN models. In particular, BONN achieves a strong generalization performance on the object detection task.

The one-versus-one (OVO) binarization decomposition scheme is considered as one of the most effective techniques to deal with multi-class classification problems. Its inherent mechanism is to use the “divide-and-conquer” strategy to decompose the multi-class classification problem into as many pairs of easier-to-solve binary sub-problems as possible. One common issue in the OVO scheme is that of non-competent classifiers. In this study, we proposed a novel OVO scheme strategy, named DRCW-FRkNN-OVO, to reduce the negative effect of non-competent classifiers. Specifically, we focused on the definition of region of competence, which plays a crucial role in managing the non-competent classifiers. To overcome the issue of skew and sparse distribution during the management of non-competent classifiers, we developed a relative competence weighting combination method via the fixed radius nearest neighbour search to find the local region within each class for the query sample. Our proposed DRCW-FRkNN-OVO is tested on 30 real-world multi-class datasets compared with several well-known related works. Experimental results supported by thorough statistical analysis confirmed the effectiveness and robustness of our proposed method.

In semiconductor foundries, wafer map defect analysis is crucial to prevent yield excursion. However, traditional manual inspection can hardly meet the high throughput demand. Deep learning based automatic defect detection shows promising efforts to achieve high accuracy and efficiency, yet the current approaches’ performance is limited by the imbalanced dataset and lack of interpretability. In this paper, we propose a Variational Autoencoder Enhanced Deep Learning Model (VAEDLM) for wafer defect imbalanced classification. It is light-weighted and effective in wafer defect pattern recognition on imbalanced dataset. It used variational autoencoder and decoder to generate similar wafer defect maps and a refined deep convolutional neural network for feature learning. We demonstrate the method using an authentic wafer map dataset, WM-811K. The performance is not only significantly improved after data augmentation, but it also beats the state-of-the art methods, reaching 99.19% accuracy, 99.10% recall, 99.23% precision, 99.96% AUC and 99.16% for F1-score. It clearly demonstrates the method’s efficacy to deal with the imbalanced defect pattern. Our study using saliency map and t-SNE further leads to enhanced interpretability.

Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition. SED naturally requires achieving two distinct supervision targets: locating fine detailed edges and identifying high-level semantics. Our motivation comes from the hypothesis that such distinct targets prevent state-of-the-art SED methods from effectively using deep supervision to improve results. To this end, we propose a novel fully convolutional neural network using diverse deep supervision (DDS) within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges. To overcome the hypothesized supervision challenge, a novel information converter unit is introduced, whose effectiveness has been extensively evaluated on SBD and Cityscapes datasets., International Journal of Computer Vision

At present, neural networks are increasingly used to solve many problems instead of traditional methods for solving them. This involves comparing the neural network and the traditional method for specific tasks. In this paper, computer modeling of the Bayesian decision rule and the probabilistic neural network is carried out in order to compare their operational characteristics for recognizing Gaussian patterns. Recognition of four and six images (classes) with the number of features from 1 to 6 was simulated in cases where the images are well and poorly separated. The sizes of the training and test samples are chosen quiet big: 500 implementations for each image. Such characteristics as training time of the decision rule, recognition time on the test sample, recognition reliability on the test sample, recognition reliability on the training sample were analyzed. In framework of these conditions it was found that the recognition reliability on the test sample in the case of well separated patterns and with any number of the instances is close to 100 percent for both decision rules. The neural network loses 0,1–16 percent to Bayesian decision rule in the recognition reliability on the test sample for poorly separated patterns. The training time of the neural network exceeds the training time of the Bayesian decision rule in 4–5 times and the recognition time – in 4–6 times. As a result, there are no obvious advantages of the probabilistic neural network over the Bayesian decision rule in the problem of Gaussian pattern recognition. The existing generalization of the Bayesian decision rule described in the article is an alternative to the neural network for the case of non-Gaussian patterns.

The existing pedestrian tracking applications are challenging to balance real-time performance and accuracy. We propose a detection–tracking–correction strategy based on the improved single-shot multi-box detector (SSD), Deep-SORT, and the improved multi-stage object detection architecture (Cascade-R-CNN), which takes both real-time performance and accuracy into consideration. For the detection mechanism, the SSD network is fast and efficient, but the disadvantage of the SSD network is relatively low accuracy. Therefore, the tricks such as cross-entropy loss function, deconvolution, and non-maximum suppression are introduced to improve the SSD network. Then, the improved SSD network is used as the central pedestrian detector to ensure real-time performance. For the tracking mechanism, the Deep-SORT is used to improve the mismatch between tracking and detection. For the correction mechanism, the improved Cascade R-CNN (introducing deformable convolution and group normalization) is used as the reference network to correct the detection errors. The experiment on the data set OTB-100 shows that the proposed strategy has good stability and adaptability in various complex scenes, and the conditions of missed detection and false detection are significantly reduced.

This study aimed to clarify whether the pattern recognition involved in scoring proliferation fractions can be trained by abstract computerized images of virtual tissues. Twenty computer-generated images with randomly distributed blue or red dots were scored by 12 probands (all co-workers or collaborators of the Institute of Pathology, University of Bonn). Afterward, the probands underwent a training phase during which they received an immediate feedback on the actual rate of positivity after each image. Finally, the initial testing series was rescored. In a second round with 15 different probands, 20 Ki-67 immunohistochemistry images of tonsil tissue were scored, followed by the same training phase with computer-generated images, before the immunohistochemistry slides were scored again. Paired t-tests were used to compare the differences in mean rates pre- and post-training. Concerning computerized images, untrained probands scored the percentages of positive dots with a mean deviation from the true rates of 8.2%. Following training, the same testing series was scored significantly better with a mean deviation of 4.9% (mean improvement 3.3%, p

Image representation is an important topic in computer vision and pattern recognition. It plays a fundamental role in a range of applications towards understanding visual contents. Moment-based image representation has been reported to be effective in satisfying the core conditions of semantic description due to its beneficial mathematical properties, especially geometric invariance and independence. This paper presents a comprehensive survey of the orthogonal moments for image representation, covering recent advances in fast/accurate calculation, robustness/invariance optimization, definition extension, and application. We also create a software package for a variety of widely-used orthogonal moments and evaluate such methods in a same base. The presented theory analysis, software implementation, and evaluation results can support the community, particularly in developing novel techniques and promoting real-world applications., Comment: ACM Computing Surveys, Volume 55, Issue 1, January 2023, Article No 1, pp 1-35, https://doi.org/10.1145/3479428

The optimal scale selection is the key problem in the study of multi-scale decision information systems. Dynamic change is one of the main features of big data, and the amount of information will often increase sharply with the passing of time. As is well known, the issue of updating the optimal scale of a multi-scale decision information system has been becoming a challenging problem in recent years, and it indeed has important theoretical and practical research values. Note that adding multiple objects can be viewed as adding one object multiple times. So, it just needs to clarify the change laws of optimal scale under the case of adding one object. Although the existing work has considered this problem in terms of the sufficient condition of updating the optimal scale, the results seem to be inaccurate. In other words, both sufficient and necessary conditions are still missing. In this paper, using sequential three-way decisions, the sufficient and necessary conditions of updating the optimal scale of a multi-scale decision information system are developed for the addition of an object, which makes the theoretical study on updating the optimal scale more complete.

Person images captured by public surveillance cameras often have low resolutions (LRs), along with uncontrolled pose variations, background clutter and occlusion. These issues cause the resolution mismatch problem when matched with high-resolution (HR) gallery images (typically available during collection), harming the person re-identification (re-id) performance. While a number of methods have been introduced based on the joint learning of super-resolution and person re-id, they ignore specific discriminant identity information encoded in LR person images, leading to ineffective model performance. In this work, we propose a novel joint bilateral-resolution identity modeling method that concurrently performs HR-specific identity feature learning with super-resolution, LR-specific identity feature learning, and person re-id optimization. We also introduce an adaptive ensemble algorithm for handling different low resolutions. Extensive evaluations validate the advantages of our method over related state-of-the-art re-id and super-resolution methods on cross-resolution re-id benchmarks. An important discovery is that leveraging LR-specific identity information enables a simple cascade of super-resolution and person re-id learning to achieve state-of-the-art performance, without elaborate model design nor bells and whistles, which has not been investigated before.