Electroencephalogram based communication system for locked in state person using mentally spelled tasks with optimized network model

In this chapter, a classifier technique that is based on a missing data estimation framework that uses autoassociative multi-layer perceptron neural networks and genetic algorithms is proposed. The proposed method is tested on a set of demographic properties of individuals obtained from the South African antenatal survey and compared to conventional feed-forward neural networks. The missing data approach based on the autoassociative network model proposed gives an accuracy of 92%, when compared to the accuracy of 84% obtained from the conventional feed-forward neural network models. The area under the receiver operating characteristics curve for the proposed autoassociative network model is 0.86 compared to 0.80 for the conventional feed-forward neural network model. The autoassociative network model proposed in this chapter, therefore, outperforms the conventional feed-forward neural network models and is an improved classifier. The reasons for this are: (1) the propagation of errors in the autoassociative network model is more distributed while for a conventional feed-forward network is more concentrated; and (2) there is no causality between the demographic properties and the HIV and, therefore, the HIV status does change the demographic properties and vice versa. Therefore, it is better to treat the problem as a missing data problem rather than a feed-forward problem.

Design of model fusion learning method based on deep bidirectional GRU neural network in fault diagnosis of industrial processes

In recent years, the Stochastic Gradient Descent (SGD) has been commonly used as an optimizer in the Conventional Neural Network (CNN) models. While many researchers have adopted CNN models to classify tasks, to the best of our knowledge, different optimizers developed for CNN have not been thoroughly studied and analyzed in the training CNNs. In this paper, attempts have been made to investigate the effects of the various optimizers on the performance of CNN. Two sets of experiments are conducted. First, for the classification of the records on the CIFAR10, MNIST, and Fashion MNIST datasets, a well-known CNN called VGG11 is trained from scratch by four different kinds of optimizers including SGD, Adam, Adadelta, and AdaGrad. Second, by the same four optimizers, a popular CNN architecture called AlexNet is fine-tuned to classify the Persian handwritten words. In both experiments, the results showed that Adam and AdaGrad have a relatively similar behavior and higher performance in comparison to the other two optimizers in terms of training cost and recognition accuracy. Also, the effect of different values of the initial learning rate on the performance of the Adam optimizer is investigated experimentally. The result revealed that lower values lead to converges more rapidly.

Diabetic retinopathy (DR) is an increasingly common eye disorder that gradually damages the retina. Identification at the early stage can significantly reduce the severity of vision loss. Deep learning techniques provide detection for retinal images based on data size and quality, as the error rate increases with low-quality images and unbalanced data classes. This paper proposes a hybrid intelligent framework of a conventional neural network and a fuzzy inference system to measure the stages of DR automatically, Diabetic Retinopathy Stage Measurement using Conventional Neural Network and Fuzzy Inference System (DRSM-CNNFIS). The fuzzy inference used human experts’ rules to overcome data dependency problems. At first, the Conventional Neural Network (CNN) model was used for feature extraction, and then fuzzy rules were used to measure diabetic retinopathy stage percentage. The framework is trained using images from Kaggle datasets (Diabetic Retinopathy Detection, 2022). The efficacy of this framework outperformed the other models with regard to accuracy, macro average precision, macro average recall, and macro average F1 score: 0.9281, 0.7142, 0.7753, and 0.7301, respectively. The evaluation results indicate that the proposed framework, without any segmentation process, has a similar performance for all the classes, while the other classification models (Dense-Net-201, Inception-ResNet ResNet-50, Xception, and Ensemble methods) have different levels of performance for each class classification.

In recent years, many image-based approaches have been proposed to classify plant species. Most methods utilized red green blue (RGB) imaging materials and designed custom features to classify the plant images using machine learning algorithms. Those works primarily focused on analyzing single-leaf images instead of live-crown images. Without considering the additional features of the leaves’ color and spatial pattern, they failed to handle cases that contained leaves similar in appearance due to the limited spectral information of RGB imaging. To tackle this dilemma, this study proposes a novel framework that combines hyperspectral imaging (HSI) and deep learning techniques for plant image classification. We built a plant image dataset containing 1,500 images of 30 different plant species taken by a 470–900 nm hyperspectral camera and designed a lightweight conventional neural network (CNN) model (LtCNN) to perform image classification. Several state-of-art CNN classifiers are chosen for comparison. The impact of using different band combinations as the network input is also investigated. Results show that using simulated RGB images achieves a kappa coefficient of nearly 0.90 while using the combination of 3-band RGB and 3-band near-infrared images can improve to 0.95. It is also found that the proposed LtCNN can obtain a satisfactory performance of plant classification (kappa = 0.95) using critical spectral features of the green edge (591 nm), red-edge (682 nm), and near-infrared (762 nm) bands. This study also demonstrates the excellent adaptability of the LtCNN model in recognizing leaf features of plant live-crown images while using a relatively smaller number of training samples than complex CNN models such as AlexNet, GoogLeNet, and VGGNet.

Nickel is a key competitive material source with commodities and economic characteristics, the price volatility of which would influence shareholder's decisions. For this reason, an accurate pattern prediction of nickel prices is a crucial concern for the strategic planning of investors in the nickel trade; however, the conventional neural network models are not effective in terms of predictive performance and suitability. So, Gaussian Processes-Long Short-Term Memory (GP-LSTM) model was suggested to learn the LSTM kernels and predict the nickel prices. However, this kernel function representation was not plenty for a huge amount of data captured from various sources. Also, it cannot completely learn dynamic, composite and structural data attributes. Therefore in this article, a Multiple-Kernel LSTM (MKLSTM) network model is proposed for learning the huge amount of data and predicting the nickel prices efficiently. The core objective of this MKLSTM model is to resolve the difficulty of adding LSTM and multiple kernel functions using data from nickel industries. This model is applied to find the significant attributes for representing suitable data. Also, the proper larger kernels for learning dynamic and structural data attributes are selected by constructing a Directed Acyclic Graph (DAG). By using the selected kernels, the MKLSTM is learned to predict the nickel price and its fluctuations. At last, the experimental results exhibit the performance of MKLSTM using the nickel price database compared to the LSTM and GP-LSTM models.

The scrutiny, identification, and verification of handwritten signatures on Certificates of Origin (C/O) is a critical task for customs authorities in preventing trade fraud. This task remains a significant challenge due to limitations in manpower and the need for manual verification amidst a vast volume of documents. Deep learning (DL) algorithms offer a valuable solution to address this issue. This paper deploys a Siamese Neural Network (SNN) model to assist customs officials in identifying and verifying handwritten signatures on C/O. The results demonstrate the superior performance of the SNN model over conventional Convolutional Neural Network (CNN) models and Machine Learning (ML) models, with accuracy, precision, recall, F1-score, and AUC values of 0.943, 0.912, 0.899, 0.905, and 0.919, respectively. The paper also provides in-depth analyses of omission cases and suggests applications of the model to support the work of customs officials.

This paper introduces an adaptive Higher Order Neural Network (HONN) model and applies it in data mining such as simulating and forecasting government taxation revenues. The proposed adaptive HONN model offers significant advantages over conventional Artificial Neural Network (ANN) models such as much reduced network size, faster training, as well as much improved simulation and forecasting errors. The generalization ability of this HONN model is explored and discussed. A new approach for determining the best number of hidden neurons is also proposed.

In order to solve the problem of excessive parameters and slow computing speed of classical neural networks, this paper uses the powerful parallel computing power of quantum computing to improve the computing speed of classical neural network models, and proposes a hybrid continuous variational quantum neural network (HCVQNN) model that can be used for network intrusion detection. The continuous variable layer of the model is realized through Gaussian gate and non-Gaussian gate, in which Gaussian gate performs operations such as quantum state weight addition and offset term setting, and non-Gaussian gate performs nonlinear operations, thereby improving the overall expression ability of the network model. In addition, aiming at the unbalanced problem of UNSW-NB15 in the network intrusion dataset, this paper proposes to design the algorithm from the feature level and the algorithm level, using the ReliefF algorithm for feature selection at the feature level, and oversampling and undersampling processing at the algorithm level by combining the Borderline-SMOTE algorithm and GMM algorithm. The classification experimental results on the UNSW-NB15 network intrusion dataset show that compared with the other two network models, the HCVQNN network model obtains higher classification accuracy and lower loss function value in both binary classification and multi-classification tasks, and the classification accuracy for minority categories is also improved.

Optimization of Artificial Neural Network (ANN) model design for prediction of macroinvertebrates in the Zwalm river basin (Flanders, Belgium)

As the metaverse continues to expand, it becomes increasingly critical to have human-centric networks that are both efficient and high-performing to optimize the user experience. Network modeling plays a fundamental role in optimizing and allocating resources efficiently, and configuring networks to satisfy the demands of diverse applications and users. Recently, traditional queuing theory-based approaches to network modeling have given way to machine learning-based methods. These methods rely on vast amounts of data for building precise models. Although high-precision simulators are ubiquitous, data collection is still an expensive and time-consuming process, resulting in a data bottleneck. In this paper, we propose a weakly supervised learning approach to modeling networks for human-centric networking in the metaverse. Specifically, we identify that queuing theory-based labels can be used to design the supervision signal at a very low cost. Therefore, we propose an approach that combines the inaccurate network modeling obtained from queuing theory-based approaches with an efficient and precise network model through only a small amount of simulation data. To make it a reality, we propose a novel neural network model that combines the powerful graph neural network and transformers. Additionally, we propose several additional supervision signals and a training algorithm to build a better network model. Experimental results demonstrate that our approach reduces the burden of data collection while achieving prediction accuracy comparable to results from large amounts of expensive simulation data. Furthermore, our approach exhibits superior generalization ability.

Maria: Accurate Prediction of MHC-II Peptide Presentation with Deep-Learning and Lymphoma Patient MHC-II Ligandome

In this paper, an evaluation of various discriminant neural networks classifiers for text- independent speaker verification problem is presented. Each person to be verified has a personalized neural network model. A new classifier called neural tree network (NTN) is also examined for this application. The memoryless feedforward neural network architecture makes decisions based on static features. Time delay neural network (TDNNs) have proved to be an efficient way to handle the dynamic nature of speech. Furthermore, a model called recurrent time delay neural networks (RTDNNs), obtained through a local feedback connection at the first hidden layer level of TDNNs is investigated. The training is carried out by backpropagation for sequence algorithm. The database used is a subset of the TIMIT database consisting of 38 speakers from the same dialect region. The NTN is compared with the MLP, TDNN, and RTDNN. It is shown that NTN is found to perform better than the other neural networks classifiers. Also, a little bit performance improvement was achieved due to the addition of temporal information for text-independent speaker verification problem using TDNNs and RTDNNs. Finally, we described the experimental results obtained using different neural network models.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Early detection of Alzheimer’s disease (AD) is critical for timely intervention and effective management. This study introduces a robust conventional neural network (CNN) model designed to classify magnetic resonance imaging (MRI) scans into four categories representing different stages of Alzheimer’s Disease progression: Non Demented, Very MildDemented, Mild Demented, and Moderate Demented. Leveraging a dataset of 6400 labeled MRI images, we employed advanced preprocessing techniques including normalization and data augmentation to optimized model training. The CNN model achieved an impressive accuracy of 95%, with a sensitivity of 93% and specificity of 90%, surpassing several benchmark models. These findings underscore the potential of CNNs as a promising tool for accurate and automated Alzheimer’s disease diagnosis. Future research will explore integrating additional biomarkers and expanding the model’s diagnostic capabilities to include more nuanced stages of AD progression, promising to reshape the landscape of neurodegenerative disease diagnostics.

Equality-constrained optimization problem captures increasing attention in the fields of computer science, control engineering, and applied mathematics. Almost all of the relevant issues suffer from kinds of intense or weak noises during the solving process, so that how to realize the noise deduction even noise elimination has increasingly become a sticky and significant problem. A lot of corresponding solving models are established for the equality-constrained optimization problem. However, the majority of them can find the optimal solution to a certain extent in the absence of noise disturbance, but few can behave a brilliant noise-resistance proficiency. On account of this discovery, a reformative noise-immune neural network (RNINN) model is constructed. In addition, the conventional gradient-based recursive neural network model and the zeroing recursive neural network model are presented to compare with the proposed RNINN model on convergence properties and noise-resistance capabilities. Lastly, the relative numerical experiment simulation and image target detection application are implemented to further elaborate on the robustness and efficiency of the RNINN model.