Search

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Memes have become a fundamental part of online communication and humour, reflecting and shaping the culture of today’s digital age. The amplified Meme culture is inadvertently endorsing and propagating casual Misogyny. This study proposes V-LTCS (Vision- Language Transformer Combination Search), a framework that encompasses all possible combinations of the most fitting Text (i.e. BERT, ALBERT, and XLM-R) and Vision (i.e. Swin, ConvNeXt, and ViT) Transformer Models to determine the backbone architecture for identifying Memes that contains misogynistic contents. All feasible Vision-Language Transformer Model combinations obtained from the recognized optimal Text and Vision Transformer Models are evaluated on two (smaller and larger) datasets using varied standard metrics (viz. Accuracy, Precision, Recall, and F1-Score). The BERT-ViT combinational Transformer Model demonstrated its efficiency on both datasets, validating its ability to serve as a backbone architecture for all subsequent efforts to recognize Multimodal Misogynous Memes.

A key problem domain inside Robotic Process Automation is the automatic discovery of workflow process schemes. Considering current process mining technologies, graph-based approaches dominate the industry. On the other hand, the conventional methods suffer from low time efficiency and varying accuracy. Machine learning-based methods can provide better efficiency, but they have significant limitations considering schema flexibility. The paper presents a novel neural network-based schema induction model for the discovery of event patterns containing parallel and optional sequences of different actors. This model can process more complex event graphs and situations than the conventional methods. The performed analysis and test results show the unique power of this approach in process schema mining. [ABSTRACT FROM AUTHOR]

The present study evaluates the application of the hybrid machine learning methods to detect changes of land use with a focus on agricultural lands through remote sensing data processing. Two spectral images by Landsat 8 were applied to train and test the machine learning model. Feed forward neural network classifier was utilized as the machine learning model in which two evolutionary algorithms including particle swarm optimization and invasive weed optimization were applied for the training process. Moreover, three conventional training methods including Levenberg–Marquardt back propagation (LM), Scaled conjugate gradient backpropagation (SCG) and BFGS quasi-Newton backpropagation (BFG) were used for comparing the robustness and reliability of the evolutionary algorithms. Based on the results in the case study, evolutionary algorithms are not a reliable method for detecting changes through the remote sensing analysis in terms of accuracy and computational complexities. Either BFG or LM is the best method to detect the agricultural lands in the present study. BFG is slightly more robust than the LM method. However, LM might be preferred for applying in the projects due to low computational complexities. [ABSTRACT FROM AUTHOR]

When radar receives target echoes to form plots, it is inevitably affected by clutter, which brings a lot of imprecise and uncertain information to target recognition. Traditional radar plot recognition algorithms often have poor performance in dealing with imprecise and uncertain information. To solve this problem, a radar plot recognition algorithm based on adaptive evidence classification (RPREC) is proposed in this paper. The RPREC can be considered as the evidence classification version under the belief functions. First, the recognition framework based on the belief functions for target, clutter, and uncertainty is created, and a deep neural network model classifier that can give the class of radar plots is also designed. Secondly, according to the classification results of each iteration round, the decision pieces of evidence are constructed and fused. Before being fused, evidence will be corrected based on the distribution of radar plots. Finally, based on the global fusion results, the class labels of all radar plots are updated, and the classifier is retrained and updated so as to iterate until all the class labels of radar plots are no longer changed. The performance of the RPREC is verified and analyzed based on the real radar plot datasets by comparison with other related methods. [ABSTRACT FROM AUTHOR]

Abstract Background Dealing with the high dimension of both neuroimaging data and genetic data is a difficult problem in the association of genetic data to neuroimaging. In this article, we tackle the latter problem with an eye toward developing solutions that are relevant for disease prediction. Supported by a vast literature on the predictive power of neural networks, our proposed solution uses neural networks to extract from neuroimaging data features that are relevant for predicting Alzheimer’s Disease (AD) for subsequent relation to genetics. The neuroimaging-genetic pipeline we propose is comprised of image processing, neuroimaging feature extraction and genetic association steps. We present a neural network classifier for extracting neuroimaging features that are related with the disease. The proposed method is data-driven and requires no expert advice or a priori selection of regions of interest. We further propose a multivariate regression with priors specified in the Bayesian framework that allows for group sparsity at multiple levels including SNPs and genes. Results We find the features extracted with our proposed method are better predictors of AD than features used previously in the literature suggesting that single nucleotide polymorphisms (SNPs) related to the features extracted by our proposed method are also more relevant for AD. Our neuroimaging-genetic pipeline lead to the identification of some overlapping and more importantly some different SNPs when compared to those identified with previously used features. Conclusions The pipeline we propose combines machine learning and statistical methods to benefit from the strong predictive performance of blackbox models to extract relevant features while preserving the interpretation provided by Bayesian models for genetic association. Finally, we argue in favour of using automatic feature extraction, such as the method we propose, in addition to ROI or voxelwise analysis to find potentially novel disease-relevant SNPs that may not be detected when using ROIs or voxels alone.

The article investigates the possibility of identifying the presence of SKOS (Simple Knowledge Organization System) relations between concepts represented by terms on the base of their vector representation in general natural language models. Several language models of the Word2Vec and GloVe families are considered, on the basis of which an artificial neural network (ANN) classifier of SKOS relations is formed. To train and test the efficiency of the classifier, datasets formed on the basis of the DBPedia and EuroVoc thesauri are used. The experiments performed have shown the high efficiency of the classifier trained using GloVe family models, while training it with use of Word2Vec models looks impossible in the bounds of considered ANN-based classifier architecture. Based on the results, a conclusion is made about the key role of taking into account the global context of the use of terms in the text for the possibility of identifying SKOS relations. [ABSTRACT FROM AUTHOR]

Remote sensing data are widely used in numerous applications. A conventional task solved using remote sensing images is their classification. The classification maps are commonly produced by some pre-trained classifiers applied either to uncompressed or compressed images where lossy compression is often needed and employed in practice due to the necessity to reduce data volume at stages of image transfer and storage. Then, the classification accuracy depends on the characteristics of an image, a classifier, and a coder used. The main subject of this paper is the factors that determine classification accuracy. One of them is compressed image quality. We fix the quality of compressed image quality characterized by the peak signal-to-noise ratio for several coders and rely on the same training approach. Our goal is twofold. First, we would like to consider classification accuracy for two approaches to classifier training: based on undistorted data and images with simulated distortions. Second, our desire is to compare the performance of different techniques of image compression. The task of this paper is to obtain an idea is it worth training the neural network classifier for uncompressed images or images of similar quality to the quality of compressed data to be classified. The coder’s influence on classification results is of special interest as well. The main results are the following. First, the classification accuracy is almost the same for classifiers trained for uncompressed and simulated compressed data for the general distortion model. Second, there is a certain difference in the classification results for different compression techniques studied. Lightly better classification results are observed for data produced by more sophisticated (modern) coders. Experiments have been carried out for two real-life three-channel Sentinel-2 images of Kharkiv and the Kharkiv region having different complexity. Four typical classes have been considered. As a conclusion, it is possible to state that either the general model of distortions must be modified or the classifier training should be performed for data produced by the corresponding compression technique.

The article investigates the possibility of identifying the presence of SKOS (Simple Knowledge Organization System) relations between concepts represented by terms on the base of their vector representation in general natural language models. Several language models of the Word2Vec and GloVe families are considered, on the basis of which an artificial neural network (ANN) classifier of SKOS relations is formed. To train and test the efficiency of the classifier, datasets formed on the basis of the DBPedia and EuroVoc thesauri are used. The experiments performed have shown the high efficiency of the classifier trained using GloVe family models, while training it with use of Word2Vec models looks impossible in the bounds of considered ANN-based classifier architecture. Based on the results, a conclusion is made about the key role of taking into account the global context of the use of terms in the text for the possibility of identifying SKOS relations.

Background: Dealing with the high dimension of both neuroimaging data and genetic data is a difficult problem in the association of genetic data to neuroimaging. In this article, we tackle the latter problem with an eye toward developing solutions that are relevant for disease prediction. Supported by a vast literature on the predictive power of neural networks, our proposed solution uses neural networks to extract from neuroimaging data features that are relevant for predicting Alzheimer's Disease (AD) for subsequent relation to genetics. The neuroimaging-genetic pipeline we propose is comprised of image processing, neuroimaging feature extraction and genetic association steps. We present a neural network classifier for extracting neuroimaging features that are related with the disease. The proposed method is data-driven and requires no expert advice or a priori selection of regions of interest. We further propose a multivariate regression with priors specified in the Bayesian framework that allows for group sparsity at multiple levels including SNPs and genes. Results: We find the features extracted with our proposed method are better predictors of AD than features used previously in the literature suggesting that single nucleotide polymorphisms (SNPs) related to the features extracted by our proposed method are also more relevant for AD. Our neuroimaging-genetic pipeline lead to the identification of some overlapping and more importantly some different SNPs when compared to those identified with previously used features. Conclusions: The pipeline we propose combines machine learning and statistical methods to benefit from the strong predictive performance of blackbox models to extract relevant features while preserving the interpretation provided by Bayesian models for genetic association. Finally, we argue in favour of using automatic feature extraction, such as the method we propose, in addition to ROI or voxelwise analysis to find potentially novel disease-relevant SNPs that may not be detected when using ROIs or voxels alone. [ABSTRACT FROM AUTHOR]

Remote sensing images have found numerous applications nowadays. A traditional outcome or intermediate result of their processing is a classification map. Such maps are usually obtained from a pre-trained classifier and it is desired to have the produced classification maps as accurately as possible. The basic subject of this article is the factors determining this accuracy. The main among them are the quality of remote sensing data and classifier type, parameters and training approach. Image quality can be degraded due to several factors. One of them is distortions introduced by lossy compression that is widely used due to a huge volume of acquired data and the necessity to sufficiently decrease their size at transmission, storage and/or dissemination stages. Because of this, the main goal of this paper is to consider classification and lossy compression jointly. In particular, this means that the classifier learning can be performed for original (uncompressed, compressed in a lossless manner) images (if they are available) as well as for compressed data at hand (offered to a user for classification and further analysis). The task of this paper is to consider and compare these two options. The first one is the classifier learning for original images and further application to compressed data, where images can be compressed with different compression ratios while producing compressed data of different quality. The second option is the use of the classifier learning for compressed images, where compression parameters for training data can be approximately the same as for the images to which the classifier is applied. The main result is that the latter methodology can provide certain benefits compared to the classifier learning for original data if one has to classify compressed remote sensing data. Simulation data are obtained for a classifier based on a convolutional neural network. As images for training and verification, four real-life three-channel (visible range) Sentinel-2 remote sensing images of Kharkiv and Kharkiv region are employed that possess different complexity of the content and have four main classes. The practical recommendations are given. In conclusion, we can state that it is worth having classifiers trained for several degrees of compression and it is reasonable to compress complex structure images with special care.

When radar receives target echoes to form plots, it is inevitably affected by clutter, which brings a lot of imprecise and uncertain information to target recognition. Traditional radar plot recognition algorithms often have poor performance in dealing with imprecise and uncertain information. To solve this problem, a radar plot recognition algorithm based on adaptive evidence classification (RPREC) is proposed in this paper. The RPREC can be considered as the evidence classification version under the belief functions. First, the recognition framework based on the belief functions for target, clutter, and uncertainty is created, and a deep neural network model classifier that can give the class of radar plots is also designed. Secondly, according to the classification results of each iteration round, the decision pieces of evidence are constructed and fused. Before being fused, evidence will be corrected based on the distribution of radar plots. Finally, based on the global fusion results, the class labels of all radar plots are updated, and the classifier is retrained and updated so as to iterate until all the class labels of radar plots are no longer changed. The performance of the RPREC is verified and analyzed based on the real radar plot datasets by comparison with other related methods.

The subject of study in this article is the features of structural organization and functioning of the improved Hamming network as a model of neural network heteroassociative memory for classification by discriminant functions. The goal is to improve the neural network classifier based on the Hamming network, which implements the criterion of maximum similarity using discriminant functions and does not have restrictions on the representation of input data (not only binary data). The tasks: analyze the capabilities of associative memory models using neural networks as an example; analyze the features of classification on the principles of discriminant analysis; develop the structure of a neural network classifier as a model of neural network heteroassociative memory; perform simulation modeling of the classification process on the example of medical diagnosis. The methods used are a mathematical model of the functioning of a neural network as a classifier, and simulation in C#. The following results have been obtained: the structure of the neural network classifier has been improved through the formation connection matrix of a hidden layer from pre-calculated coefficients of linear discriminant functions, and the connection matrix of the output layer in the form symmetrical matrix with zeros on the main diagonal. This allows not only to simplify m connections, where m is the number of classes, in the structure of the output layer of the neural network classifier, but also to speed up the classification process, as well as to implement classification by the maximum of discriminant functions. Conclusions. The scientific novelty of the results obtained is as follows: the neural network classification method has been improved using pre-calculated elements of the connection matrices in the hidden and output layers of the classifier, which does not imply a long process of direct neural network learning with using discriminant functions; the structural organization of a neural network classifier is proposed, which is an improvement of the Hamming network as a model of heteroassociative memory, that allows using this classifier in a decision support system for medical diagnosis; the removal of positive feedback in neurons of the competitive (output) layer is implemented, which allows not only simplifies the structure of the neural network classifier but also speeds up the classification process almost 2 times, which is confirmed by the simulation results.

Purpose: To describe the relationships between foveal structure and visual function in a cohort of individuals with foveal hypoplasia (FH) and to estimate FH grade and visual acuity using a deep learning classifier. Design: Retrospective cohort study and experimental study. Participants: A total of 201 patients with FH were evaluated at the National Eye Institute from 2004 to 2018. Methods: Structural components of foveal OCT scans and corresponding clinical data were analyzed to assess their contributions to visual acuity. To automate FH scoring and visual acuity correlations, we evaluated the following 3 inputs for training a neural network predictor: (1) OCT scans, (2) OCT scans and metadata, and (3) real OCT scans and fake OCT scans created from a generative adversarial network. Main Outcome Measures: The relationships between visual acuity outcomes and determinants, such as foveal morphology, nystagmus, and refractive error. Results: The mean subject age was 24.4 years (range, 1–73 years; standard deviation = 18.25 years) at the time of OCT imaging. The mean best-corrected visual acuity (n = 398 eyes) was equivalent to a logarithm of the minimal angle of resolution (LogMAR) value of 0.75 (Snellen 20/115). Spherical equivalent refractive error (SER) ranged from −20.25 diopters (D) to +13.63 D with a median of +0.50 D. The presence of nystagmus and a high-LogMAR value showed a statistically significant relationship (P < 0.0001). The participants whose SER values were farther from plano demonstrated higher LogMAR values (n = 382 eyes). The proportion of patients with nystagmus increased with a higher FH grade. Variability in SER with grade 4 (range, −20.25 D to +13.00 D) compared with grade 1 (range, −8.88 D to +8.50 D) was statistically significant (P < 0.0001). Our neural network predictors reliably estimated the FH grading and visual acuity (correlation to true value > 0.85 and > 0.70, respectively) for a test cohort of 37 individuals (98 OCT scans). Training the predictor on real OCT scans with metadata and fake OCT scans improved the accuracy over the model trained on real OCT scans alone. Conclusions: Nystagmus and foveal anatomy impact visual outcomes in patients with FH, and computational algorithms reliably estimate FH grading and visual acuity.

The paper presents results of using a neural network classifier to analyze images of malignant skin lesions obtained using a hyper-spectral camera. Using a three-block neural network of VGG architecture, we conducted the classification of a set of two-dimensional images of melanoma, papilloma and basal cell carcinoma, obtained in the range of 530 – 570 and 600 – 606 nm, characterized by the highest absorption of melanin and hemoglobin. The sufficiency of the inclusion in the training set of two-dimensional images of a limited spectral range is analyzed. The results obtained show significant prospects of using neural network algorithms for processing hyperspectral data for the classification of skin pathologies. With a relatively small set of training data used in the study, the classification accuracy for the three types of neoplasms was as high as 96 %.

Facial expression recognition (FER) requires better descriptors to represent the face patterns as the facial region changes due to the movement of the face muscles during an expression. In this paper, a method of concatenating spatial pyramid Zernike moments based shape features and Law’s texture features is proposed to uniquely capture the macro and micro details of each facial expression. The proposed method employs multilayer perceptron and radial basis function feed forward artificial neural networks for recognizing the facial expressions. The suitability of the features in recognizing the expressions is explored across the datasets independent of the subjects or persons. The experiments conducted on JAFFE and KDEF datasets demonstrate that the concatenated feature vectors are capable of representing the facial expressions with better accuracy and least errors. The radial basis function based classifier delivers a performance with an average recognition accuracy of 95.86% and 88.87% on the JAFFE and KDEF datasets respectively for subject dependent FER.

This research builds a human action recognition system based on a single image or video capture snapshot. The TensorFlow Deep Learning models are developed using human keypoints generated by OpenPose. Four classifiers are considered: Neural Network, Random Forest, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM) Classifiers. The models’ input layer are 50 points from x and y coordinate of 25 keypoints from OpenPose, and the output layer is the numerical representation of 11 human action labels which are 'hand-wave', 'jump', 'leg-cross', 'plank', 'ride', 'run', 'sit', 'lay-down', 'squat', 'stand', 'walk’. A total of 2132 images dataset was used for model training and testing. The results show the two best classifier models: Neural Network Classifier with 512 hidden nodes with an accuracy of 0.7733, and Random Forest Classifier with 60 estimators with an accuracy of 0.7752. Both models are then used as inference engines to recognize human action from images and real-time video. [ABSTRACT FROM AUTHOR]

The problem of continuous hidden user authentication based on the analysis of keyboard handwriting is considered. The main purpose of the analysis is to continuously verify the identity of the subject during his work on the keyboard. The aim of the work is to increase the efficiency of hidden user authentication algorithms based on a neural network analysis of a dynamic profile, formed by keyboard handwriting. The idea of user authentication using keyboard handwriting is based on measuring the time of keystrokes and the intervals between keystrokes, followed by comparing the resulting data set with the stored dynamic user profile. Studies have shown that analyzing the average value of the time each key is pressed is inefficient. It is proposed to analyze the holding time of a combination of several keys and the time between their presses. An approach in which not the times of pressing individual keys, but the parameters of pressing the most common letter combinations are analyzed, will increase the accuracy of recognition of dynamic images. An algorithm and software implementation for Russian keyboard layout have been developed, experiments conducted on field data allow us to conclude that the proposed method is effectively used to authenticate the user using keyboard handwriting.

Iris identification plays an important role in many applications like security, banking, access to buildings, and surveillance …. etc. Since the iris part of the eye image can be significantly affected by some factors, such as lighting conditions source, eyelids, eyelashes, pupil, sclera, and shadowing, therefore iris identification research is still wide and rich. The work proposed in this paper operates the iris identification system on the distorted colored images captured under visible light. The proposed idea minimizes the number of iris regions affected by distortion, by dividing the iris region into separable regions. Only the region without distortion part or region with distortion is less probable is used. The paper studies the effect of different color model such as HSV, YIQ, YCbCr, and RGB color models on iris identification. High quality feature extraction is introduced in this paper by using Contourlet Transform (CT). Euclidian Distance (ED) or Neural Network (NN) is used as classifiers. Simulation results show that the proposed method operating on non-distortion iris region outperforms the conventional method operating on the whole iris region for any selected color model and for standard databases (UPOL andUTIRIS) and a suggested one.

Background: Infrared (IR) spectroscopy allows intraoperative, optical brain tumor diagnosis. Here, we explored it as a translational technology for the identification of aggressive meningioma types according to both, the WHO CNS grading system and the methylation classes (MC)., Methods: Frozen sections of 47 meningioma were examined by IR spectroscopic imaging and different classification approaches were compared to discern samples according to WHO grade or MC., Results: IR spectroscopic differences were more pronounced between WHO grade 2 and 3 than between MC intermediate and MC malignant, although similar spectral ranges were affected. Aggressive types of meningioma exhibited reduced bands of carbohydrates (at 1024 cm -1 ) and nucleic acids (at 1080 cm -1 ), along with increased bands of phospholipids (at 1240 and 1450 cm -1 ). While linear discriminant analysis was able to discern spectra of WHO grade 2 and 3 meningiomas (AUC 0.89), it failed for MC (AUC 0.66). However, neural network classifiers were effective for classification according to both WHO grade (AUC 0.91) and MC (AUC 0.83), resulting in the correct classification of 20/23 meningiomas of the test set., Conclusions: IR spectroscopy proved capable of extracting information about the malignancy of meningiomas, not only according to the WHO grade, but also for a diagnostic system based on molecular tumor characteristics. In future clinical use, physicians could assess the goodness of the classification by considering classification probabilities and cross-measurement validation. This might enhance the overall accuracy and clinical utility, reinforcing the potential of IR spectroscopy in advancing precision medicine for meningioma characterization., Competing Interests: None., (© The Author(s) 2024. Published by Oxford University Press, the Society for Neuro-Oncology and the European Association of Neuro-Oncology.)

In the banking industry, credit card evolution is a noticeable occurrence. Each banking system includes a huge dataset for customer's transactions of their credit cards. Therefore, banks would be in need of customer profiling. Profiling bank customer's cognize the issuer's decisions about whom to give banking facilities and what a credit limit to provide. It also helps the issuers get a better understanding of their potential and current customers. In previous research, Customer profiling mainly depends on transaction data or demographic data, but in this research, we merge both data in order to get a more accurate result and minimize the risk. By finding the best technique, it leads to improvement in accuracy and helps banks to get higher profitability by customer satisfaction through a focus on the valuable customer (companies) which consider as the main engine in the bank's profitability. This study aims at using k-mean, improved k-mean, fuzzy c-means and neural networks. The used dataset is labeled and creating a ýnew label as a target for neural network classification is the main aspect of this study, which helps to reduce the clustering execution time and get the best accuracy results. Finally, by comparing the accuracy ratio it shows that the neural network ýis the best clustering technique.

In this paper, an Advanced Quantum-based Neural Network Classifier (AQNN) is proposed. The proposed AQNN is used to form an objectionable Web content filtering system (OWF). The aim is to design a neural network with a few numbers of hidden layer neurons with the optimal connection weights and the threshold of neurons. The proposed algorithm uses the concept of quantum computing and genetic concept to evolve connection weights and the threshold of neurons. Quantum computing uses qubit as a probabilistic representation which is the smallest unit of information in the quantum computing concept. In this algorithm, a threshold boundary parameter is also introduced to find the optimal value of the threshold of neurons. The proposed algorithm forms neural network architecture which is used to form an objectionable Web content filtering system which detects objectionable Web request by the user. To judge the performance of the proposed AQNN, a total of 2000 (1000 objectionable + 1000 non-objectionable) Website's contents have been used. The results of AQNN are also compared with QNN-F and well-known classifiers as backpropagation, support vector machine (SVM), multilayer perceptron, decision tree algorithm, and artificial neural network. The results show that the AQNN as classifier performs better than existing classifiers. The performance of the proposed objectionable Web content filtering system (OWF) is also compared with well-known objectionable Web filtering software and existing models. It is found that the proposed OWF performs better than existing solutions in terms of filtering objectionable content.

One of the most prevalent forms of cancer worldwide is oral cancer which has a high rate of mortality. Diagnosis and treatment of oral premalignant lesions at an early stage reduces the death rate. The objective of this work is to detect malignancies by analyzing color features of digital true color oral images. A dataset of around 433 oral lesion images has been created that includes benign, premalignant and malignant lesions. The proposed method was experimented on this dataset. Different classifiers have been trained using various color features. The neural network classifier detects abnormalities with an accuracy of 94.82%. Results indicate that the color features have better potential in identifying benign and malignant oral lesions. [ABSTRACT FROM AUTHOR]

Electrical impedance tomography (EIT) uses non-invasive and non-radiative imaging to detect inhomogeneous electrical properties in tissues. The inverse problem of EIT is a highly nonlinear, ill-posed problem, which causes inaccuracy in target size calculation. We propose a novel approach to discretize the target size and use a neural network (NN) classifier to classify the unknown size in discrete steps. The target size is discretized into distinct steps, and each step can be a unique class. The data is pre-processed with the cumulative distribution transform (CDT) to enhance distinguishability. First, the NN is trained with simulated datasets, divided into time difference (t-d) group and CDT group. After training, the NN classifier is tested by experimental data recorded in a phantom experiment. Linear discriminant analysis (LDA) is performed to assess the distinguishability of classes. There is a significant increase in distance between classes after the CDT pre-processing. The density of the classes has an upward trend with a higher degree of clustering after CDT pre-processing. The CDT data clustering into distinguishable classes is essential to excellent NN classification results. Such an approach is a significant paradigm shift by turning the cumbersome inverse calculation with uncertain accuracy into a classification problem with predetermined step errors. The accuracy and resolution can be further extended by increasing the discretization steps. [ABSTRACT FROM AUTHOR]

Sarcasm is a type of sentiment where people express negative sentiment using positive connotation words in text and vice-versa. In this work, we propose a cross-domain sarcasm detection framework that allows acquisition, storage and processing of tweets for detecting sarcastic content in online reviews. We conduct our experiments on Amazon product review dataset namely the Sarcasm Corpus Version1 having about 2000 reviews. We use Support Vector Machines (SVM) and Neural Networks (NN) for detecting sarcasm using lexical, pragmatic, linguistic incongruity and context incongruity features. We report the results and present a comparative evaluation of SVM and NN classifiers for single domain sarcasm detection indicating their suitability for the task. Then, we use these models for cross-domain sarcasm detection. The experimental results indicate the reliability of our approach.

Electrocardiogram (ECG), a non-invasive diagnostic technique, used for detecting cardiac arrhythmia. From last decade industry dealing with biomedical instrumentation and research, demanding an advancement in its ability to distinguish different cardiac arrhythmia. Atrial Fibrillation (AF) is an irregular rhythm of the human heart. During AF, the atrial moments are quicker than the normal rate. As blood is not completely ejected out of atria, chances for the formation of blood clots in atrium. These abnormalities in the heart can be identified by the changes in the morphology of the ECG. The first step in the detection of AF is preprocessing of ECG, which removes noise using filters. Feature extraction is the next key process in this research. Recent feature extraction methods, such as Auto Regressive (AR) modeling, Magnitude Squared Coherence (MSC) and Wavelet Coherence (WTC) using standard database (MIT-BIH), yielded a lot of features. Many of these features might be insignificant containing some redundant and non-discriminatory features that introduce computational burden and loss of performance. This paper presents fast Conjugate Symmetric Sequency Ordered Complex Hadamard Transform (CS-SCHT) for extracting relevant features from the ECG signal. The sparse matrix factorization method is used for developing fast and efficient CS-SCHT algorithm and its computational performance is examined and compared to that of the HT and NCHT. The applications of the CS-SCHT in the ECG-based AF detection is also discussed. These fast CS-SCHT features are optimized using Hybrid Firefly and Particle Swarm Optimization (FFPSO) to increase the performance of the classifier.

Introduction: The COVID-19 pandemic had a global impact and created an unprecedented emergency in healthcare and other related frontline sectors. Various Artificial-Intelligence-based models were developed to effectively manage medical resources and identify patients at high risk. However, many of these AI models were limited in their practical high-risk applicability due to their "black-box" nature, i.e., lack of interpretability of the model. To tackle this problem, Explainable Artificial Intelligence (XAI) was introduced, aiming to explore the "black box" behavior of machine learning models and offer definitive and interpretable evidence. XAI provides interpretable analysis in a human-compliant way, thus boosting our confidence in the successful implementation of AI systems in the wild., Methods: In this regard, this study explores the use of model-agnostic XAI models, such as SHapley Additive exPlanations values (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), for COVID-19 symptom analysis in Indian patients toward a COVID severity prediction task. Various machine learning models such as Decision Tree Classifier, XGBoost Classifier, and Neural Network Classifier are leveraged to develop Machine Learning models., Results and Discussion: The proposed XAI tools are found to augment the high performance of AI systems with human interpretable evidence and reasoning, as shown through the interpretation of various explainability plots. Our comparative analysis illustrates the significance of XAI tools and their impact within a healthcare context. The study suggests that SHAP and LIME analysis are promising methods for incorporating explainability in model development and can lead to better and more trustworthy ML models in the future., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Nambiar, S and S.)

Machine learning-guided optical proximity correction, called ML-OPC in this paper, has recently been proposed to alleviate long runtime of model-based OPC. ML-OPC using regression methods has been presented but with limited prediction accuracy. We propose neural network classifier-based OPC (NNC-OPC), in which a neural network classifier serves as a mask bias model. A few techniques are applied to enhance basic NNC-OPC: parameterization of layout segments using polar Fourier transform signals, dimensionality reduction through weighted principal component analysis, and sampling of training layout segments. Training segments are typically imbalanced over the range of mask biases, which may cause large prediction error for segments that appear less frequently. This is resolved by three techniques: 1) synthetic data generation; 2) class reorganization; and 3) an adaptive learning rate. Experiments with NNC-OPC with all techniques applied indicate that prediction error of mask bias and training time are reduced by 29% and 80%, respectively, compared to state-of-the-art ML-OPC with regression methods. [ABSTRACT FROM AUTHOR]

This paper presents a two-stage algorithm for automatic text detection and recognition. In the first stage, using a stroke width transform and an improved connected component, an edge analysis method detects a candidate character region. Subsequently, a text region is located by filtering and linking characters with similar font sizes and colors. For the second stage, a histogram of oriented gradient is employed as a feature descriptor, and a neural network classifier is built with dynamic-group-based hybrid particle swarm optimization (DGHPSO) for character recognition. In DGHPSO, each group's threshold value of similarity depends on the threshold values of fitness and distance. In addition, a local search algorithm is used to improve the search for a global optimum. The proposed algorithm was experimentally validated; it outperformed a number of recently published studies in terms of the text recognition rate when tested on the ICDAR 2003 database and the Street View Text database. [ABSTRACT FROM AUTHOR]

Highlights • Robust multi-parametric NCO-tracking controllers do not entail a discretization of the continuous-time dynamics. • The robust-counterpart multi-parametric dynamic optimization (mp-DO) problem retains the same complexity as nominal mp-DO. • Data classifiers based on deep learning can accurately describe the critical regions in (nominal or robust) mp-DO. • The methodology is demonstrated for a fluid catalytic cracking (FCC) unit and a chemical reactor cascade. Abstract This paper presents an extension of the recent multi-parametric (mp-)NCO-tracking methodology by Sun et al. [Comput. Chem. Eng. 92 (2016) 64–77] for the design of robust multi-parametric controllers for constrained continuous-time linear systems in the presence of uncertainty. We propose a robust-counterpart formulation and solution of multi-parametric dynamic optimization (mp-DO), whereby the constraints are backed-off based on a worst-case propagation of the uncertainty using either interval analysis or ellipsoidal calculus and an ancillary linear state feedback. We address the case of additive uncertainty, and we discuss approaches to dealing with multiplicative uncertainty that retain tractability of the mp-NCO-tracking design problem, subject to extra conservativeness. In order to assist with the implementation of these controllers, we also investigate the use of data classifiers based on deep learning for approximating the critical regions in continuous-time mp-DO problems, and subsequently searching for a critical region during on-line execution. We illustrate these developments with the case studies of a fluid catalytic cracking (FCC) unit and a chemical reactor cascade. [ABSTRACT FROM AUTHOR]

A new simulation and processing methodology based on open source tools to produce high fidelity synthetic aperture radar (SAR) simulations of ground vehicles of varying types, as well as analysis of an applied automatic target recognition (ATR) technique is presented in this Letter. This work is based around the RaySAR open‐source model and the outputs have been configured for both monostatic and bistatic geometries. Input CAD models of various military and civilian vehicles are used to produce the SAR imagery. This output imagery was then used to train a tiny you only look once convolutional neural network (CNN) classifier. The classification success of the CNN applied was showed to produce significantly accurate results and the whole pipeline of processing enabled rapid evaluation of potential ATR methods against targets of choice. [ABSTRACT FROM AUTHOR]

The nearest neighbor partitioning (NNP) method is a high performance approach which is used for improving traditional neural network classifiers. However, the construction process of NNP model is very time-consuming, particularly for large data sets, thus limiting its range of application. In this study, a parallel NNP method is proposed to accelerate NNP based on Compute Unified Device Architecture(CUDA). In this method, blocks and threads are used to evaluate potential neural networks and to perform parallel subtasks, respectively. Experimental results manifest that the proposed parallel method improves performance of NNP neural network classifier. Furthermore, the application of parallel NNP in performance evaluation of cement microstructure indicates that the proposed approach has favorable performance. [ABSTRACT FROM AUTHOR]

In this study, a framework to super resolve and recognise the long range captured iris polar images is proposed. The proposed framework consists of best frame selection algorithm, modified diamond search algorithm, Gaussian process regression (GPR) based and enhanced iterated back projection (EIBP)‐based super‐resolution approach, fuzzy entropy‐based feature selector and neural network (NN) classifier. The framework uses linear kernel co‐variance function in local patch‐based GPR and EIBP algorithms and it super resolves the iris images depending on the contents of the patches, without an external dataset. NN classifier classifies the iris images by using features extracted using discrete cosine transform domain based no‐reference image quality assessment model, Gray level co‐occurrence matrix, Hu seven moments and statistical features. The framework is tested using CASIA long range iris database by comparing and analysing the peak signal‐to‐noise ratio, structural similarity index matrix and visual information fidelity in pixel domain of proposed algorithms with Yang and Nguyen framework. The results demonstrate that the proposed framework is well suited for recognition of iris images captured at a long distance. [ABSTRACT FROM AUTHOR]

Objective: By modeling the cochlear implant (CI) electrode-to-nerve interface and quantifying electrode discriminability in the model, we address the questions of how many individual channels can be distinguished by CI recipients and the extent to which performance might be improved by inserting electrodes deeper into the cochlea. Method: We adapt an artificial neural network to model electrode discrimination as well as a commonly used psychophysical measure (four-interval forced-choice) in CI stimulation and predict how well the locations of the stimulating electrodes can be inferred from simulated auditory nerve spiking patterns. Results: We show that a longer electrode leads to better electrode place discrimination in our model. For a simulated four-interval forced-choice procedure, correct classification rates significantly reduce with decreasing distance between the test electrodes and the reference electrodes, and higher correct classification rates may be achieved by the basal electrodes than apical electrodes. Conclusion: Our results suggest that enhanced electrode discriminability results from a longer CI electrode array, and the locations where the errors occur along the electrode array are not only affected by the distance between electrodes but also the twirling angle between electrodes. Significance: Our models and simulations provide theoretical insights into several important clinically relevant problems that will inform future designs of CI electrode arrays and stimulation strategies. [ABSTRACT FROM AUTHOR]

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases.

High resolution digital cameras and state-of-the-art image editing software tools has given rise to large amount of manipulated images leaving no traces of being subjected to any manipulation. Passive or blind forgery detection algorithms are used in order to determine its authenticity. In this paper, an algorithm is proposed that blindly detects global rescaling operation using the statistical models computed based on quadrature mirror filter (QMF) decomposition. Fuzzy entropy measure is employed to choose the relevant features and to remove non-important features whereas artificial neural network classifier is used for forgery detection. Experimental results are presented on grayscale and -component images of UCID database to prove the validity of the algorithm under different interpolation schemes. Results are provided for the detection of rescaled images with JPEG compression, arbitrary cropping and white Gaussian noise addition. Further, results are shown using USC-SIPI database to prove the robustness of the algorithm against the type of database. [ABSTRACT FROM AUTHOR]