Traditional Pattern Recognition Research Articles

Artificial Intelligence in Forensic Sciences Revolution or Invasion? Part II

Aim: The study is on the emerging role of artificial intelligence in the forensic sciences. After clarifying the basic concepts and a brief historical overview, the possibilities of using AI in various forensic fields are discussed: genetics, pattern recognition, chemistry, toxicology, anthropology, forensic medicine, and scene reconstruction. Methodology: The study synthesises several recently published international papers. Findings: The penetration of the application of artificial intelligence into some fields of science is undoubtedly an ongoing process. Most of the varied forensic fields also cannot avoid this development. Analysing large databases unmanageable with traditional methods, pattern recognition, and machine learning can all be important tools for forensic science. However, an important conclusion is that AI is a supporter of human expert work, not a substitute. Value: In the field of forensic sciences, no such detailed summary article has been published in Hungarian so far.

Mesterséges intelligencia a törvényszéki tudományokban Revolúció vagy invázió? II. rész

Aim: The study is on the emerging role of artificial intelligence in the forensic sciences. After clarifying the basic concepts and a brief historical overview, the possibilities of using AI in various forensic fields are discussed: genetics, pattern recognition, chemistry, toxicology, anthropology, forensic medicine, and scene reconstruction. Methodology: The study synthesises several recently published international papers. Findings: The penetration of the application of artificial intelligence into some fields of science is undoubtedly an ongoing process. Most of the varied forensic fields also cannot avoid this development. Analysing large databases unmanageable with traditional methods, pattern recognition, and machine learning can all be important tools for forensic science. However, an important conclusion is that AI is a supporter of human expert work, not a substitute. Value: In the field of forensic sciences, no such detailed summary article has been published in Hungarian so far.

LINEAR REGRESSION-BASED ANALYSIS OF MULTIMEDIA DATA FOR AI-DRIVEN PATTERN RECOGNITION

Multimedia data, encompassing images, videos, and audio, has become a cornerstone in various AI-driven applications, particularly in pattern recognition tasks. The increasing complexity and volume of multimedia data necessitate robust and scalable analytical approaches. Traditional pattern recognition techniques often struggle to effectively manage the high-dimensional and multimodal nature of multimedia data. This study addresses the challenge by leveraging linear regression for analyzing multimedia data to enhance AI-driven pattern recognition. The proposed method integrates linear regression models with feature extraction techniques to identify and map underlying patterns within the multimedia data. The process begins with preprocessing steps, including normalization and dimensionality reduction, to ensure data consistency and manage computational complexity. Subsequently, linear regression models are applied to establish relationships between the extracted features and predefined classes or labels. The model’s performance is evaluated using precision, recall, and F1-score metrics. Experimental results on a benchmark multimedia dataset reveal that the proposed approach achieves an average accuracy of 92.4%, with a precision of 91.8% and a recall of 93.1%. These results outperform several state-of-the-art methods, demonstrating the model’s efficacy in accurately recognizing patterns within diverse multimedia data. Furthermore, the model exhibits scalability, maintaining high performance even when applied to large-scale datasets, thus validating its potential for real-world AI applications. The study concludes that linear regression, when integrated with appropriate feature extraction and preprocessing techniques, offers a viable solution for enhancing AI-driven pattern recognition in multimedia data.

RPC-EAU: Radar Plot Classification Algorithm Based on Evidence Adaptive Updating

Accurately classifying targets and clutter plots is crucial in radar data processing. It is beneficial for filtering out a large amount of clutters and improving the track initiation speed and tracking accuracy of real targets. However, in practical applications, this problem becomes difficult due to complex electromagnetic environments such as cloud and rain clutter, sea clutter, and strong ground clutter. This has led to poor performance of some commonly used radar plot classification algorithms. In order to solve this problem and further improve classification accuracy, the radar plot classification algorithm based on evidence adaptive updating (RPC-EAU) is proposed in this paper. Firstly, the multi-dimensional recognition features of radar plots used for classification are established. Secondly, the construction and combination of mass functions based on feature sample distribution are designed. Then, a confidence network classifier containing an uncertain class was designed, and an iterative update strategy for it was provided. Finally, several experiments based on synthetic and real radar plots were presented. The results show that RPC-EAU can effectively improve the radar plot classification performance, achieving a classification accuracy of about 0.96 and a clutter removal rate of 0.95. Compared with some traditional radar pattern recognition algorithms, it can improve by 1 to 10 percentage points. The target loss rate of RPC-EAU is also the lowest, only about 0.02, which is about one third to one half of the comparison algorithms. In addition, RPC-EAU avoids clustering all radar points in each update, greatly saving the computational time. The proposed algorithm has the characteristics of high classification accuracy, low target loss rate, and less computational time. Therefore, it is suitable for radar data processing with high timeliness requirements and multiple radar plots.

Artificial Intelligence in Forensic SciencesRevolution or Invasion? Part I

Aim: The first half of the two-part study is on the emerging role of artificial intelligence in the forensic sciences. After clarifying the basic concepts and a brief historical overview, the possibilities of using AI in various forensic fields are discussed: genetics, pattern recognition, chemistry, toxicology, anthropology, forensic medicine, and scene reconstruction. Methodology: The study synthesises several recently published international papers. Findings: The penetration of the application of artificial intelligence into some fields of science is undoubtedly an ongoing process. Most of the varied forensic fields also cannot avoid this development. Analysing large databases unmanageable with traditional methods, pattern recognition, and machine learning can all be important tools for forensic science. However, an important conclusion is that AI is a supporter of human expert work, not a substitute. Value: In the field of forensic sciences, no such detailed summary article has been published in Hungarian so far.

Artificial Intelligence in Forensic Sciences Revolution or Invasion?

Aim: The first half of the two-part study is on the emerging role of artificial intelligence in the forensic sciences. After clarifying the basic concepts and a brief historical overview, the possibilities of using AI in various forensic fields are discussed: genetics, pattern recognition, chemistry, toxicology, anthropology, forensic medicine, and scene reconstruction. Methodology: The study synthesises several recently published international papers. Findings: The penetration of the application of artificial intelligence into some fields of science is undoubtedly an ongoing process. Most of the varied forensic fields also cannot avoid this development. Analysing large databases unmanageable with traditional methods, pattern recognition, and machine learning can all be important tools for forensic science. However, an important conclusion is that AI is a supporter of human expert work, not a substitute. Value: In the field of forensic sciences, no such detailed summary article has been published in Hungarian so far.

Multi-bolt looseness positioning using multivariate recurrence analytic active sensing method and MHAMCNN model

The piezoelectric active sensing method has been proven to be an effective, nondestructive approach for bolt looseness monitoring. The conventional damage index relies on the energy index of the wavelet packet. However, the method of wavelet packet could not identify the looseness location of the multi-bolt. Therefore, an innovative multi-bolt intelligent method combined the multivariate recurrence analytic active sensing method with an improved convolutional neural network (CNN) model was proposed for multi-bolt looseness positioning. In this method, the multivariate recurrence plots (RPs) are firstly constructed based on the received stress waves and then it is utilized to extract the recursive attributes presented within the stress wave signals. Secondly, a novel model, the CNN improved by the multi-head attention mechanism (MHAMCNN), is constructed to extract nonlinear features hidden in multivariate RPs. Repeated experiments demonstrate that the proposed method, which combines MHAMCNN and un-thresholded multivariate RPs (i.e., mean detection accuracy: 98.62%), outperformed other methods, including multivariate RPs (i.e., mean detection accuracy: 97.06%) and common RPs. Compared with traditional pattern recognition algorithms, MHAMCNN has higher classification accuracy. In summary, the suggested approach presents a promising opportunity for the real-time monitoring of multi-bolt looseness.

Study on vibration signals identification method for pipeline leakage detection based on deep learning technology

For natural gas pipeline leakage systems based on distributed feedback fiber laser vibration sensors (DFB-FL), a novel neural network model (mCNN-LFLBs) integrating multi-scale convolutional neural networks (mCNN) with local feature extraction blocks (LFLBs) is proposed in this study. To address the problem of feature loss in the traditional signal image transfer process, the one-dimensional original signal is directly used as the input of the model, effectively maintaining the time-domain correlation of the leaked signal. The time-domain correlation of the leakage signal is preserved. To address the problem that traditional pattern recognition algorithms have a weak ability to extract deep features and local features, mCNN is established by this model, which realizes the use of convolution kernels of different scales to extract features of different frequency bands in one-dimensional signals. Additionally, LFLBs are introduced, which enhances the local expression ability of the model, further improves the feature mining quality of the model, and better presents the deep features of leaked signals. Experimental results demonstrate that the mCNN-LFLBs model has a classification accuracy of up to 98.6%, with a testing response time of approximately 10 ms, and outstanding performance in terms of convergence speed. These results highlight the potential practical application of the mCNN-LFLBs model in natural gas leak detection.

Semantic-aware automatic extraction method for bottom sediment annotations in raster nautical charts

ABSTRACT The automatic extraction of bottom sediment annotations in large-scale raster nautical charts has limitations, including an imprecise semantic information description and low efficiency. To overcome them, we propose a convolutional neural network (CNN)-based method for the automatic extraction of bottom sediment annotations in raster nautical charts, using image processing techniques to improve it. First, an adaptive chart partitioning model that considers element completeness is constructed. Second, a principle for the unique identification of elements based on spatial conflicts is designed. Finally, a model for accurately extracting semantic information for bottom sediment annotations is established. To evaluate the effectiveness of the proposed method, we implemented a model based on the PyTorch framework and used the PIL library to analyze the results. We also conducted comparative experiments on multiple CNN models to recommend the selection of such models in the proposed method by comparing their classification and recognition performance. The experimental results indicate that (1) the proposed model can achieve high-precision extraction of bottom sediment annotations in raster nautical charts. (2) Furthermore, the proposed model generally has high recognition accuracy and semantic completeness, with better recognition precision than traditional pattern recognition methods.

Unsupervised domain adaptation with deep network based on discriminative class-wise MMD

<abstract> <p>General learning algorithms trained on a specific dataset often have difficulty generalizing effectively across different domains. In traditional pattern recognition, a classifier is typically trained on one dataset and then tested on another, assuming both datasets follow the same distribution. This assumption poses difficulty for the solution to be applied in real-world scenarios. The challenge of making a robust generalization from data originated from diverse sources is called the domain adaptation problem. Many studies have suggested solutions for mapping samples from two domains into a shared feature space and aligning their distributions. To achieve distribution alignment, minimizing the maximum mean discrepancy (MMD) between the feature distributions of the two domains has been proven effective. However, this alignment of features between two domains ignores the essential class-wise alignment, which is crucial for adaptation. To address the issue, this study introduced a discriminative, class-wise deep kernel-based MMD technique for unsupervised domain adaptation. Experimental findings demonstrated that the proposed approach not only aligns the data distribution of each class in both source and target domains, but it also enhances the adaptation outcomes.</p> </abstract>

A multiscale bidirectional fuzzy-driven learning network for remote sensing image segmentation

ABSTRACT Semantic segmentation is a fundamental but meaningful task in the remote sensing image understanding community. Great progress has been made in optical sensor photography technology, which poses an opportunity and a challenge for remote sensing image segmentation task. But, in fact, a longstanding and intractable problem is that many hard pixels in special position, i.e. the prevalent intra-class noise and a poor boundary delineation, is difficult to classify due to their inherent uncertainty. In this paper, we comprehensively consider the characteristics of deep learning and introduce traditional pattern recognition methods to drive structure learning, which can leverage the corresponding fuzzy logic model to alleviate the aforementioned problem in remote sensing images. Specifically, this paper designs a multiscale bidirectional fuzzy-driven learning network (MBFNet), which takes advantage of both deep learning and fuzzy logic to effectively alleviate the inherent uncertainty of these hard pixels. The structure of convolutional neural networks driven by fuzzy systems also provides a new modelling paradigm for solving the uncertain problem in remote sensing images. Meanwhile, multiscale techniques and bidirectional fusion are introduced to enhance feature aggregation and avoid the potential adverse effects of fuzzy systems, respectively. Experimental results on two datasets demonstrate qualitatively and quantitatively that the proposed MBFNet is competitive.

Intelligent perception of tandem flapping wings' flow field environment with sparse detectors

Bionic flapping wing vehicles have great potential for civil and defense applications due to their flexibility and concealment at low Reynolds numbers. Since traditional flow field pattern recognition methods are difficult to identify effective information from the measured local flow field and deduce the state information of the moving body, this study uses an artificial intelligence method to establish the internal correlation between flow field pattern and state information. Specifically, a fully connected neural network is adopted to recognize the tandem flapping wings' flow field pattern by using different data acquisition methods and detector array distribution methods. Compared with the neural network based on time series data, the neural network based on spatial distribution data can realize the real-time judgment of flow field environment, which is closer to the real-time requirements in practical applications. In the paper, the intelligent perception of multi-flapping wings' flow field environment with sparse detectors is carried out and lays the theoretical foundation for autonomous navigation and obstacle avoidance of flapping wing aircrafts.

Pipeline visualization based on RIR-RepVGG network

Electrical Capacitance Tomography (ECT) is a process tomography technology based on capacitance-sensitive field, which is of vital importance to accelerate the development of industrial intelligence by measuring the required capacitance data through sensors to achieve the flow pattern detection of filled pipes and thus meet the controllability of pipe flow patterns. The traditional ECT flow pattern recognition method has low recognition rate and more complicated operation. In this paper, the detection method of filling pipeline is studied based on electrical capacitance tomography (ECT) technology. Aiming at the low imaging accuracy of traditional ECT reconstruction algorithms, an ECT image reconstruction method based on improved residual neural network was proposed. The RIR-RepVGG residual network structure is proposed and a nonlinear mapping network is designed. The improved residual network is used to establish the mapping relationship between the capacitance vector and the two-phase flow image. Through the static study by filling pipeline simulation experiments and static experiments, it is proved that the ECT image reconstruction method proposed in this paper can reduce the artifacts and deformation of the reconstructed image, improve the reconstruction accuracy, and has a better reconstruction effect for complex flow patterns. Application is of great significance.

Open set classification of untranscribed handwritten text image documents

Content-based classification of manuscripts is an important task that is generally carried out by expert archivists. Nevertheless, many historical manuscript collections are so vast that in most cases this task is hardly feasible, even for large, well staffed archives. Nowadays, manuscripts are generally preserved in the form of sets of digital images. Therefore, the technical problem we are interested in is automatic classification of “‘image documents”, each consisting of a set of untranscribed handwritten text images, by the textual contents of the images. The traditional Pattern Recognition classification paradigm does provide the basic tools to deal with this problem. However, in practice, the set of relevant classes of a large documental series is seldom known in advance. Therefore, a classifier trained with a predefined set of classes will systematically fail when new image documents arrive which do not belong to any of the classes assumed in training. Here we adopt the “Open Set Classification” framework to extend and consolidate our previous work on image document classification in order to adequately handle new documents from unknown classes. The proposed approaches are based on a relatively novel technology for text image representation known as “probabilistic indexing”, which proves very effective to characterise the intrinsic word-level uncertainty exhibited by historical handwritten text images. We assess the performance of this approach on a moderately sized but representative dataset extracted from a huge series of complex notarial manuscripts from the Spanish Archivo Histórico Provincial de Cádiz, with good results.

Learning by Seeing More Classes.

Traditional pattern recognition models usually assume a fixed and identical number of classes during both training and inference stages. In this paper, we study an interesting but ignored question: can increasing the number of classes during training improve the generalization and reliability performance? For a k-class problem, instead of training with only these k classes, we propose to learn with k+m classes, where the additional m classes can be either real classes from other datasets or synthesized from known classes. Specifically, we propose two strategies for constructing new classes from known classes. By making the model see more classes during training, we can obtain several advantages. Firstly, the added m classes serve as a regularization which is helpful to improve the generalization accuracy on the original k classes. Secondly, this will alleviate the overconfident phenomenon and produce more reliable confidence estimation for different tasks like misclassification detection, confidence calibration, and out-of-distribution detection. Lastly, the additional classes can also improve the learned feature representation, which is beneficial for new classes generalization in few-shot learning and class-incremental learning. Compared with the widely proved concept of data augmentation (dataAug), our method is driven from another dimension of augmentation based on additional classes (classAug). Comprehensive experiments demonstrated the superiority of our classAug under various open-environment metrics on benchmark datasets.

Amphid sensory neurons of Caenorhabditis elegans orchestrate its survival from infection with broad classes of pathogens.

The survival of a host during infection relies on its ability to rapidly sense the invading pathogen and mount an appropriate response. The bacterivorous nematode Caenorhabditis elegans lacks most of the traditional pattern recognition mechanisms. In this study, we hypothesized that the 12 pairs of amphid sensory neurons in the heads of worms provide sensing capability and thus affect survival during infection. We tested animals lacking amphid neurons to three major classes of pathogens, namely-a Gram-negative bacterium Pseudomonas aeruginosa, a Gram-positive bacterium Enterococcus faecalis, and a pathogenic yeast Cryptococcus neoformans By using individual neuronal ablation lines or mutants lacking specific neurons, we demonstrate that some neurons broadly suppress the survival of the host and colonization of all pathogens, whereas other amphid neurons differentially regulate host survival during infection. We also show that the roles of some of these neurons are pathogen-specific, as seen with the AWB odor sensory neurons that promote survival only during infections with P aeruginosa Overall, our study reveals broad and specific roles for amphid neurons during infections.

Data-driven discovery of innate immunomodulators via machine learning-guided high throughput screening.

The innate immune response is vital for the success of prophylactic vaccines and immunotherapies. Control of signaling in innate immune pathways can improve prophylactic vaccines by inhibiting unfavorable systemic inflammation and immunotherapies by enhancing immune stimulation. In this work, we developed a machine learning-enabled active learning pipeline to guide in vitro experimental screening and discovery of small molecule immunomodulators that improve immune responses by altering the signaling activity of innate immune responses stimulated by traditional pattern recognition receptor agonists. Molecules were tested by in vitro high throughput screening (HTS) where we measured modulation of the nuclear factor κ-light-chain-enhancer of activated B-cells (NF-κB) and the interferon regulatory factors (IRF) pathways. These data were used to train data-driven predictive models linking molecular structure to modulation of the NF-κB and IRF responses using deep representational learning, Gaussian process regression, and Bayesian optimization. By interleaving successive rounds of model training and in vitro HTS, we performed an active learning-guided traversal of a 139 998 molecule library. After sampling only ∼2% of the library, we discovered viable molecules with unprecedented immunomodulatory capacity, including those capable of suppressing NF-κB activity by up to 15-fold, elevating NF-κB activity by up to 5-fold, and elevating IRF activity by up to 6-fold. We extracted chemical design rules identifying particular chemical fragments as principal drivers of specific immunomodulation behaviors. We validated the immunomodulatory effect of a subset of our top candidates by measuring cytokine release profiles. Of these, one molecule induced a 3-fold enhancement in IFN-β production when delivered with a cyclic di-nucleotide stimulator of interferon genes (STING) agonist. In sum, our machine learning-enabled screening approach presents an efficient immunomodulator discovery pipeline that has furnished a library of novel small molecules with a strong capacity to enhance or suppress innate immune signaling pathways to shape and improve prophylactic vaccination and immunotherapies.

GIS Partial Discharge Pattern Recognition Based on Multi-Feature Information Fusion of PRPD Image

Partial discharge (PD) pattern recognition is a critical indicator for evaluating the insulation state of gas-insulated switchgear (GIS). Aiming at the disadvantage of traditional PD pattern recognition methods, such as single feature extraction and low recognition accuracy, a pattern recognition method of PD based on multi-feature information fusion is proposed in this paper. Firstly, a recognition model based on quasi-Hausdorff distance is established according to the statistical characteristics of the phase-resolved partial discharge (PRPD) image, and then a modified convolutional neural network recognition model is established according to the image features of the PRPD image. Finally, Dempster–Shafer (D–S) evidence theory is used to fuse the two pattern recognition results and complement the advantages of the two approaches to improve the accuracy of partial discharge pattern recognition. The experimental results show that the total recognition accuracy rate of this method for four typical PD is more than 94.00%, and the recognition rate is significantly improved compared to support vector machine and normal convolution neural network. Maintaining stability in typical bipedal robots is challenging due to two main reasons.

Increasing The Taxonomic Accuracy of Remote Sensing Data Using Traditional Pattern Recognition Methods

The most significant outcomes of remote sensing are maps of Land Use and Land Cover (LULC), which can be controlled by a procedure known as image classification. Using image processing methods, we are developing a system in this effort to categorize satellite photos and extract information. Satellite pictures have been classified into usable and unused areas, as well as sub-classifying each class into numerous further classes. Used satellite photos are further divided into residential, commercial, highway, and agricultural areas, while unused images are divided into forest, river, desert, and beach areas. Since K-means classifiers analyze images features and Otsu's approach for multilevel image thresholding is efficient for automatic classification of satellite images, that is the main topic of this research.

Appearance quality classification method of Huangguan pear under complex background based on instance segmentation and semantic segmentation.

The 'Huangguan' pear disease spot detection and grading is the key to fruit processing automation. Due to the variety of individual shapes and disease spot types of 'Huangguan' pear. The traditional computer vision technology and pattern recognition methods have some limitations in the detection of 'Huangguan' pear diseases. In recent years, with the development of deep learning technology and convolutional neural network provides a new solution for the fast and accurate detection of 'Huangguan' pear diseases. To achieve automatic grading of 'Huangguan' pear appearance quality in a complex context, this study proposes an integrated framework combining instance segmentation, semantic segmentation and grading models. In the first stage, Mask R-CNN and Mask R-CNN with the introduction of the preprocessing module are used to segment 'Huangguan' pears from complex backgrounds. In the second stage, DeepLabV3+, UNet and PSPNet are used to segment the 'Huangguan' pear spots to get the spots, and the ratio of the spot pixel area to the 'Huangguan' pear pixel area is calculated and classified into three grades. In the third stage, the grades of 'Huangguan' pear are obtained using ResNet50, VGG16 and MobileNetV3. The experimental results show that the model proposed in this paper can segment the 'Huangguan' pear and disease spots in complex background in steps, and complete the grading of 'Huangguan' pear fruit disease severity. According to the experimental results. The Mask R-CNN that introduced the CLAHE preprocessing module in the first-stage instance segmentation model is the most accurate. The resulting pixel accuracy (PA) is 97.38% and the Dice coefficient is 68.08%. DeepLabV3+ is the most accurate in the second-stage semantic segmentation model. The pixel accuracy is 94.03% and the Dice coefficient is 67.25%. ResNet50 is the most accurate among the third-stage classification models. The average precision (AP) was 97.41% and the F1 (harmonic average assessment) was 95.43%.In short, it not only provides a new framework for the detection and identification of 'Huangguan' pear fruit diseases in complex backgrounds, but also lays a theoretical foundation for the assessment and grading of 'Huangguan' pear diseases.