At present, there are widespread financing difficulties in China's trade circulation industry. Supply chain finance can provide financing for small- and medium-sized enterprises in China's trade circulation industry, but it will produce financing risks such as credit risks. It is necessary to analyze the causes of the risks in the supply chain finance of the trade circulation industry and measure these risks by establishing a credit risk assessment system. In this article, a supply chain financial risk early warning index system is established, including 4 first-level indicators and 29 third-level indicators. Then, on the basis of the supply chain financial risk early warning index system, combined with the method of convolution neural network, the supply chain financial risk early warning model of trade circulation industry is constructed, and the evaluation index is measured by the method of principal component analysis. Finally, the relevant data of trade circulation enterprises are selected to make an empirical analysis of the model. The conclusion shows that the supply chain financial risk early warning model and risk control measures established in this article have certain reference value for the commercial circulation industry to carry out supply chain finance. It also provides guidance for trade circulation enterprises to deal with supply chain financial risks effectively.
Sleep disorder is a symptom of many neurological diseases that may significantly affect the quality of daily life. Traditional methods are time-consuming and involve the manual scoring of polysomnogram (PSG) signals obtained in a laboratory environment. However, the automated monitoring of sleep stages can help detect neurological disorders accurately as well. In this study, a flexible deep learning model is proposed using raw PSG signals. A one-dimensional convolutional neural network (1D-CNN) is developed using electroencephalogram (EEG) and electrooculogram (EOG) signals for the classification of sleep stages. The performance of the system is evaluated using two public databases (sleep-edf and sleep-edfx). The developed model yielded the highest accuracies of 98.06%, 94.64%, 92.36%, 91.22%, and 91.00% for two to six sleep classes, respectively, using the sleep-edf database. Further, the proposed model obtained the highest accuracies of 97.62%, 94.34%, 92.33%, 90.98%, and 89.54%, respectively for the same two to six sleep classes using the sleep-edfx dataset. The developed deep learning model is ready for clinical usage, and can be tested with big PSG data.
Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional neural network (CNN) with two convolutional layers, two down-sampling layers, and a fully connected layer is proposed in this work. The same 1D data was transformed into two-dimensional (2D) images to improve the model's classification accuracy. Then, we applied the 2D CNN model consisting of input and output layers, three 2D-convolutional layers, three down-sampling layers, and a fully connected layer. The classification accuracy of 97.38% and 99.02% is achieved with the proposed 1D and 2D model when tested on the publicly available Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Both proposed 1D and 2D CNN models outperformed the corresponding state-of-the-art classification algorithms for the same data, which validates the proposed models' effectiveness.
This paper attempts to solve the typical problems of self-organizing growing network models, i.e. (a) an influence of the order of input data on the self-organizing ability, (b) an instability to high-dimensional data and an excessive sensitivity to noise, and (c) an expensive computational cost by integrating Kernel Bayes Rule (KBR) and Correntropy-Induced Metric (CIM) into Adaptive Resonance Theory (ART) framework. KBR performs a covariance-free Bayesian computation which is able to maintain a fast and stable computation. CIM is a generalized similarity measurement which can maintain a high-noise reduction ability even in a high-dimensional space. In addition, a Growing Neural Gas (GNG)-based topology construction process is integrated into the ART framework to enhance its self-organizing ability. The simulation experiments with synthetic and real-world datasets show that the proposed model has an outstanding stable self-organizing ability for various test environments.
This study outlines and developed a multilayer perceptron (MLP) neural network model for adolescent hypertension classification focusing on the use of simple anthropometric and sociodemographic data collected from a cross-sectional research study in Sarawak, Malaysia. Among the 2,461 data collected, 741 were hypertensive (30.1%) and 1720 were normal (69.9%). During the data gathering process, eleven anthropometric measurements and sociodemographic data were collected. The variable selection procedure in the methodology proposed selected five parameters: weight, weight-to-height ratio (WHtR), age, sex, and ethnicity, as the input of the network model. The developed MLP model with a single hidden layer of 50 hidden neurons managed to achieve a sensitivity of 0.41, specificity of 0.91, precision of 0.65, F-score of 0.50, accuracy of 0.76, and Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.75 using the imbalanced data set. Analyzing the performance metrics obtained from the training, validation and testing data sets show that the developed network model is well-generalized. Using Bayes' Theorem, an adolescent classified as hypertensive using this created model has a 66.2% likelihood of having hypertension in the Sarawak adolescent population, which has a hypertension prevalence of 30.1%. When the prevalence of hypertension in the Sarawak population was increased to 50%, the developed model could predict an adolescent having hypertension with an 82.0% chance, whereas when the prevalence of hypertension was reduced to 10%, the developed model could only predict true positive hypertension with a 33.6% chance. With the sensitivity of the model increasing to 65% and 90% while retaining a specificity of 91%, the true positivity of an adolescent being hypertension would be 75.7% and 81.2%, respectively, according to Bayes' Theorem. The findings show that simple anthropometric measurements paired with sociodemographic data are feasible to be used to classify hypertension in adolescents using the developed MLP model in Sarawak adolescent population with modest hypertension prevalence. However, a model with higher sensitivity and specificity is required for better positive hypertension predictive value when the prevalence is low. We conclude that the developed classification model could serve as a quick and easy preliminary warning tool for screening high-risk adolescents of developing hypertension.
The human respiratory system is affected when an individual is infected with COVID-19, which became a global pandemic in 2020 and affected millions of people worldwide. However, accurate diagnosis of COVID-19 can be challenging due to small variations in typical and COVID-19 pneumonia, as well as the complexities involved in classifying infection regions. Currently, various deep learning (DL)-based methods are being introduced for the automatic detection of COVID-19 using computerized tomography (CT) scan images. In this paper, we propose the pelican optimization algorithm-based long short-term memory (POA-LSTM) method for classifying coronavirus using CT scan images. The data preprocessing technique is used to convert raw image data into a suitable format for subsequent steps. Here, we develop a general framework called no new U-Net (nnU-Net) for region of interest (ROI) segmentation in medical images. We apply a set of heuristic guidelines derived from the domain to systematically optimize the ROI segmentation task, which represents the dataset's key properties. Furthermore, high-resolution net (HRNet) is a standard neural network design developed for feature extraction. HRNet chooses the top-down strategy over the bottom-up method after considering the two options. It first detects the subject, generates a bounding box around the object and then estimates the relevant feature. The POA is used to minimize the subjective influence of manually selected parameters and enhance the LSTM's parameters. Thus, the POA-LSTM is used for the classification process, achieving higher performance for each performance metric such as accuracy, sensitivity, F1-score, precision, and specificity of 99%, 98.67%, 98.88%, 98.72%, and 98.43%, respectively.
This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF-FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model's performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF-FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF-FFA model can be applied as an efficient technique for the accurate prediction of vertical handover.
Alzheimer's Disease (AD) is a neurodegenerative irreversible brain disorder that gradually wipes out the memory, thinking skills and eventually the ability to carry out day-to-day tasks. The amount of AD patients is rapidly increasing due to several lifestyle changes that affect biological functions. Detection of AD at its early stages helps in the treatment of patients. In this paper, a predictive and preventive model that uses biomarkers such as the amyloid-beta protein is proposed to detect, predict, and prevent AD onset. A Convolution Neural Network (CNN) based model is developed to predict AD at its early stages. The results obtained proved that the proposed model outperforms the traditional Machine Learning (ML) algorithms such as Logistic Regression, Support Vector Machine, Decision Tree Classifier, and K Nearest Neighbor algorithms.
Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.
In this paper, two approaches were introduced to obtain Stackelberg solutions for two-level linear fractional programming problems with interval coefficients in the objective functions. The approaches were based on the Kth best method and the method for solving linear fractional programming problems with interval coefficients in the objective function. In the first approach, linear fractional programming with interval coefficients in the objective function and linear programming were utilized to obtain Stackelberg solution, but in the second approach only linear programming is used. Since a linear fractional programming with interval coefficients can be equivalently transformed into a linear programming, therefore both of approaches have same results. Numerical examples demonstrate the feasibility and effectiveness of the methods.
Gross domestic product (GDP) is an important indicator for determining a country's or region's economic status and development level, and it is closely linked to inflation, unemployment, and economic growth rates. These basic indicators can comprehensively and effectively reflect a country's or region's future economic development. The center of radial basis function neural network and smoothing factor to take a uniform distribution of the random radial basis function artificial neural network will be the focus of this study. This stochastic learning method is a useful addition to the existing methods for determining the center and smoothing factors of radial basis function neural networks, and it can also help the network more efficiently train. GDP forecasting is aided by the genetic algorithm radial basis neural network, which allows the government to make timely and effective macrocontrol plans based on the forecast trend of GDP in the region. This study uses the genetic algorithm radial basis, neural network model, to make judgments on the relationships contained in this sequence and compare and analyze the prediction effect and generalization ability of the model to verify the applicability of the genetic algorithm radial basis, neural network model, based on the modeling of historical data, which may contain linear and nonlinear relationships by itself, so this study uses the genetic algorithm radial basis, neural network model, to make, compare, and analyze judgments on the relationships contained in this sequence.
Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.
The major compounds in honey are carbohydrates such as monosaccharides and disaccharides. The same compounds are found in cane-sugar concentrates. Unfortunately when sugar concentrate is added to honey, laboratory assessments are found to be ineffective in detecting this adulteration. Unlike tracing heavy metals in honey, sugar adulterated honey is much trickier and harder to detect, and traditionally it has been very challenging to come up with a suitable method to prove the presence of adulterants in honey products. This paper proposes a combination of array sensing and multi-modality sensor fusion that can effectively discriminate the samples not only based on the compounds present in the sample but also mimic the way humans perceive flavours and aromas. Conversely, analytical instruments are based on chemical separations which may alter the properties of the volatiles or flavours of a particular honey. The present work is focused on classifying 18 samples of different honeys, sugar syrups and adulterated samples using data fusion of electronic nose (e-nose) and electronic tongue (e-tongue) measurements. Each group of samples was evaluated separately by the e-nose and e-tongue. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were able to separately discriminate monofloral honey from sugar syrup, and polyfloral honey from sugar and adulterated samples using the e-nose and e-tongue. The e-nose was observed to give better separation compared to e-tongue assessment, particularly when LDA was applied. However, when all samples were combined in one classification analysis, neither PCA nor LDA were able to discriminate between honeys of different floral origins, sugar syrup and adulterated samples. By applying a sensor fusion technique, the classification for the 18 different samples was improved. Significant improvement was observed using PCA, while LDA not only improved the discrimination but also gave better classification. An improvement in performance was also observed using a Probabilistic Neural Network classifier when the e-nose and e-tongue data were fused.
Using bone char for contaminated wastewater treatment and soil remediation is an intriguing approach to environmental management and an environmentally friendly way of recycling waste. The bone char remediation strategy for heavy metal-polluted wastewater was primarily affected by bone char characteristics, factors of solution, and heavy metal (HM) chemistry. Therefore, the optimal parameters of HM sorption by bone char depend on the research being performed. Regarding enhancing HM immobilization by bone char, a generic strategy for determining optimal parameters and predicting outcomes is crucial. The primary objective of this research was to employ artificial neural network (ANN) technology to determine the optimal parameters via sensitivity analysis and to predict objective function through simulation. Sensitivity analysis found that for multi-metals sorption (Cd, Ni, and Zn), the order of significance for pyrolysis parameters was reaction temperature > heating rate > residence time. The primary variables for single metal sorption were solution pH, HM concentration, and pyrolysis temperature. Regarding binary sorption, the incubation parameters were evaluated in the following order: HM concentrations > solution pH > bone char mass > incubation duration. This approach can be used for further experiment design and improve the immobilization of HM by bone char for water remediation.
Wireless capsule endoscopy (WCE) is one of the most efficient methods for the examination of gastrointestinal tracts. Computer-aided intelligent diagnostic tools alleviate the challenges faced during manual inspection of long WCE videos. Several approaches have been proposed in the literature for the automatic detection and localization of anomalies in WCE images. Some of them focus on specific anomalies such as bleeding, polyp, lesion, etc. However, relatively fewer generic methods have been proposed to detect all those common anomalies simultaneously. In this paper, a deep convolutional neural network (CNN) based model 'WCENet' is proposed for anomaly detection and localization in WCE images. The model works in two phases. In the first phase, a simple and efficient attention-based CNN classifies an image into one of the four categories: polyp, vascular, inflammatory, or normal. If the image is classified in one of the abnormal categories, it is processed in the second phase for the anomaly localization. Fusion of Grad-CAM++ and a custom SegNet is used for anomalous region segmentation in the abnormal image. WCENet classifier attains accuracy and area under receiver operating characteristic of 98% and 99%. The WCENet segmentation model obtains a frequency weighted intersection over union of 81%, and an average dice score of 56% on the KID dataset. WCENet outperforms nine different state-of-the-art conventional machine learning and deep learning models on the KID dataset. The proposed model demonstrates potential for clinical applications.
This study proposes a deep convolutional neural network for the automatic segmentation of glioblastoma brain tumors, aiming sat replacing the manual segmentation method that is both time-consuming and labor-intensive. There are many challenges for automatic segmentation to finely segment sub-regions from multi-sequence magnetic resonance images because of the complexity and variability of glioblastomas, such as the loss of boundary information, misclassified regions, and subregion size. To overcome these challenges, this study introduces a spatial pyramid module and attention mechanism to the automatic segmentation algorithm, which focuses on multi-scale spatial details and context information. The proposed method has been tested in the public benchmarks BraTS 2018, BraTS 2019, BraTS 2020 and BraTS 2021 datasets. The Dice score on the enhanced tumor, whole tumor, and tumor core were respectively 79.90 %, 89.63 %, and 85.89 % on the BraTS 2018 dataset, respectively 77.14 %, 89.58 %, and 83.33 % on the BraTS 2019 dataset, and respectively 77.80 %, 90.04 %, and 83.18 % on the BraTS 2020 dataset, and respectively 83.48 %, 90.70 %, and 88.94 % on the BraTS 2021 dataset offering performance on par with that of state-of-the-art methods with only 1.90 M parameters. In addition, our approach significantly reduced the requirements for experimental equipment, and the average time taken to segment one case was only 1.48 s; these two benefits rendered the proposed network intensely competitive for clinical practice.
The electrocardiogram (ECG) is a standard test used to monitor the activity of the heart. Many cardiac abnormalities will be manifested in the ECG including arrhythmia which is a general term that refers to an abnormal heart rhythm. The basis of arrhythmia diagnosis is the identification of normal versus abnormal individual heart beats, and their correct classification into different diagnoses, based on ECG morphology. Heartbeats can be sub-divided into five categories namely non-ectopic, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats. It is challenging and time-consuming to distinguish these heartbeats on ECG as these signals are typically corrupted by noise. We developed a 9-layer deep convolutional neural network (CNN) to automatically identify 5 different categories of heartbeats in ECG signals. Our experiment was conducted in original and noise attenuated sets of ECG signals derived from a publicly available database. This set was artificially augmented to even out the number of instances the 5 classes of heartbeats and filtered to remove high-frequency noise. The CNN was trained using the augmented data and achieved an accuracy of 94.03% and 93.47% in the diagnostic classification of heartbeats in original and noise free ECGs, respectively. When the CNN was trained with highly imbalanced data (original dataset), the accuracy of the CNN reduced to 89.07%% and 89.3% in noisy and noise-free ECGs. When properly trained, the proposed CNN model can serve as a tool for screening of ECG to quickly identify different types and frequency of arrhythmic heartbeats.
We are exposed to various chemical compounds present in the environment, cosmetics, and drugs almost every day. Mutagenicity is a valuable property that plays a significant role in establishing a chemical compound's safety. Exposure and handling of mutagenic chemicals in the environment pose a high health risk; therefore, identification and screening of these chemicals are essential. Considering the time constraints and the pressure to avoid laboratory animals' use, the shift to alternative methodologies that can establish a rapid and cost-effective detection without undue over-conservation seems critical. In this regard, computational detection and identification of the mutagens in environmental samples like drugs, pesticides, dyes, reagents, wastewater, cosmetics, and other substances is vital. From the last two decades, there have been numerous efforts to develop the prediction models for mutagenicity, and by far, machine learning methods have demonstrated some noteworthy performance and reliability. However, the accuracy of such prediction models has always been one of the major concerns for the researchers working in this area. The mutagenicity prediction models were developed using deep neural network (DNN), support vector machine, k-nearest neighbor, and random forest. The developed classifiers were based on 3039 compounds and validated on 1014 compounds; each of them encoded with 1597 molecular feature vectors. DNN-based prediction model yielded highest prediction accuracy of 92.95% and 83.81% with the training and test data, respectively. The area under the receiver's operating curve and precision-recall curve values were found to be 0.894 and 0.838, respectively. The DNN-based classifier not only fits the data with better performance as compared to traditional machine learning algorithms, viz., support vector machine, k-nearest neighbor, and random forest (with and without feature reduction) but also yields better performance metrics. In current work, we propose a DNN-based model to predict mutagenicity of compounds.
The huge number of voxels in fMRI over time poses a major challenge to for effective analysis. Fast, accurate, and reliable classifiers are required for estimating the decoding accuracy of brain activities. Although machine-learning classifiers seem promising, individual classifiers have their own limitations. To address this limitation, the present paper proposes a method based on the ensemble of neural networks to analyze fMRI data for cognitive state classification for application across multiple subjects. Similarly, the fuzzy integral (FI) approach has been employed as an efficient tool for combining different classifiers. The FI approach led to the development of a classifiers ensemble technique that performs better than any of the single classifier by reducing the misclassification, the bias, and the variance. The proposed method successfully classified the different cognitive states for multiple subjects with high accuracy of classification. Comparison of the performance improvement, while applying ensemble neural networks method, vs. that of the individual neural network strongly points toward the usefulness of the proposed method.
Deep learning (DL) models are becoming pervasive and applicable to computer vision, image processing, and synthesis problems. The performance of these models is often improved through architectural configuration, tweaks, the use of enormous training data, and skillful selection of hyperparameters. The application of deep learning models to medical image processing has yielded interesting performance, capable of correctly detecting abnormalities in medical digital images, making them surpass human physicians. However, advancing research in this domain largely relies on the availability of training datasets. These datasets are sometimes not publicly accessible, insufficient for training, and may also be characterized by a class imbalance among samples. As a result, inadequate training samples and difficulty in accessing new datasets for training deep learning models limit performance and research into new domains. Hence, generative adversarial networks (GANs) have been proposed to mediate this gap by synthesizing data similar to real sample images. However, we observed that benchmark datasets with regions of interest (ROIs) for characterizing abnormalities in breast cancer using digital mammography do not contain sufficient data with a fair distribution of all cases of abnormalities. For instance, the architectural distortion and breast asymmetry in digital mammograms are sparsely distributed across most publicly available datasets. This paper proposes a GAN model, named ROImammoGAN, which synthesizes ROI-based digital mammograms. Our approach involves the design of a GAN model consisting of both a generator and a discriminator to learn a hierarchy of representations for abnormalities in digital mammograms. Attention is given to architectural distortion, asymmetry, mass, and microcalcification abnormalities so that training distinctively learns the features of each abnormality and generates sufficient images for each category. The proposed GAN model was applied to MIAS datasets, and the performance evaluation yielded a competitive accuracy for the synthesized samples. In addition, the quality of the images generated was also evaluated using PSNR, SSIM, FSIM, BRISQUE, PQUE, NIQUE, FID, and geometry scores. The results showed that ROImammoGAN performed competitively with state-of-the-art GANs. The outcome of this study is a model for augmenting CNN models with ROI-centric image samples for the characterization of abnormalities in breast images.