Explore the vast range of titles available.

Analysis of microarray data is a highly challenging problem due to the inherent complexity in the nature of the data associated with higher dimensionality, smaller sample size, imbalanced number of classes, noisy data-structure, and higher variance of feature values. This has led to lesser classification accuracy and over-fitting problem. In this work, the authors aimed to develop a deep feedforward method to classify the given microarray cancer data into a set of classes for subsequent diagnosis purposes. They have used a 7-layer deep neural network architecture having various parameters for each dataset. The small sample size and dimensionality problems are addressed by considering a well-known dimensionality reduction technique namely principal component analysis. The feature values are scaled using the Min–Max approach and the proposed approach is validated on eight standard microarray cancer datasets. To measure the loss, a binary cross-entropy is used and adaptive moment estimation is considered for optimisation. The performance of the proposed approach is evaluated using classification accuracy, precision, recall, f-measure, log-loss, receiver operating characteristic curve, and confusion matrix. A comparative analysis with state-of-the-art methods is carried out and the performance of the proposed approach exhibit better performance than many of the existing methods.

Classification of plastic materials based on spectroscopic data is a very crucial task in a variety of applications, including automated recycling, environmental monitoring, quality control in manufacturing, quality control of products, and analysis of complex material properties. These applications demand high precision in identifying and separating plastic types to enhance sustainability and ensure regulatory compliance. In this work, we presented a novel technique Hybridized Attention mechanism-based Feedforward Neural Network (HAttFFNN) to detect three stage Polyethylene Terephthalate (PET) materials. Dataset used in this methodology is basically comprised of 295,327 samples, and contains the parameters like absorbance, wavelengths, references, samples. We collected the spectral data (900-1700 nm) using the Digital Light Processing (DLP) Near-Infrared (NIR) scan Nano Evaluation Module (EVM). We utilized various preprocessing techniques for better and improved detection result, such as Savitzky-Golay filter, interference, Standard Normal Variate (SNV) and Multiplicative Scatter Correction (MSC). The preprocessed and organized spectral data is provided to the proposed HAttFFNN model for the detection of three stage PET material. To validate the performance of the proposed model, we experimented various State-Of-The-Art (SOTA) models, Multi-Head Neural Network (MHNN), Virtual Geometry Group (VGG16), One-Dimensional Convolutional Neural Network (1D-CNN), Residual Network (ResNet), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The proposed model outperforms state of the art techniques across all metrics including accuracy, precision, recall, F1 score, and specificity with Stage 1 (PET Clear vs PET Hazard) achieving 99.33% accuracy, Stage 2 (PET vs Others) 99.32%, and Stage 3 (PET Coloured vs PET Transparent) 99.28%, along with consistently high precision, recall, and specificity values for each class. These results confirm that our proposed model, HAttFFNN, is able to achieve higher accuracy in spectroscopic classification domain, especially in complex cases such as differentiating between visually and spectrally similar materials (PET Clear vs PET Hazard, PET vs Others and PET Colored vs PET Transparent) where traditional models often fail. Furthermore, the Root Mean Square Error (RMSE) values 0.1408 for Stage 1, 0.1249 for Stage 2, and 0.1403 for Stage 3, further validate the model's low-error performance, reinforcing its effectiveness as a less error-prone approach for spectrometry-based plastic material classification.

Experimental and computational data and field data obtained from measurements are often sparse and noisy. Consequently, interpolating unknown functions under these restrictions to provide accurate predictions is very challenging. This study compares machine-learning methods and cubic splines on the sparsity of training data they can handle, especially when training samples are noisy. We compare deviation from a true function f using the mean square error, signal-to-noise ratio and the Pearson R2 coefficient. We show that, given very sparse data, cubic splines constitute a more precise interpolation method than deep neural networks and multivariate adaptive regression splines. In contrast, machine-learning models are robust to noise and can outperform splines after a training data threshold is met. Our study aims to provide a general framework for interpolating one-dimensional signals, often the result of complex scientific simulations or laboratory experiments.

Convolutional neural networks (CNNs) are the specific architecture of feed‐forward artificial neural networks. It is the de‐facto standard for various operations in machine learning and computer vision. To transform this performance towards the task of network anomaly detection in cyber‐security, this study proposes a model using one‐dimensional CNN architecture. The authors' approach divides network traffic data into transmission control protocol (TCP), user datagram protocol (UDP), and OTHER protocol categories in the first phase, then each category is treated independently. Before training the model, feature selection is performed using the Chi‐square technique, and then, over‐sampling is conducted using the synthetic minority over‐sampling technique to tackle a class imbalance problem. The authors' method yields the weighted average f‐score 0.85, 0.97, 0.86, and 0.78 for TCP, UDP, OTHER, and ALL categories, respectively. The model is tested on the UNSW‐NB15 dataset.

PurposeThe purpose of this paper is to conduct a comprehensive review of the noteworthy contributions made in the area of the Feedforward neural network (FNN) to improve its generalization performance and convergence rate (learning speed); to identify new research directions that will help researchers to design new, simple and efficient algorithms and users to implement optimal designed FNNs for solving complex problems; and to explore the wide applications of the reviewed FNN algorithms in solving real-world management, engineering and health sciences problems and demonstrate the advantages of these algorithms in enhancing decision making for practical operations.Design/methodology/approachThe FNN has gained much popularity during the last three decades. Therefore, the authors have focused on algorithms proposed during the last three decades. The selected databases were searched with popular keywords: “generalization performance,” “learning rate,” “overfitting” and “fixed and cascade architecture.” Combinations of the keywords were also used to get more relevant results. Duplicated articles in the databases, non-English language, and matched keywords but out of scope, were discarded.FindingsThe authors studied a total of 80 articles and classified them into six categories according to the nature of the algorithms proposed in these articles which aimed at improving the generalization performance and convergence rate of FNNs. To review and discuss all the six categories would result in the paper being too long. Therefore, the authors further divided the six categories into two parts (i.e. Part I and Part II). The current paper, Part I, investigates two categories that focus on learning algorithms (i.e. gradient learning algorithms for network training and gradient-free learning algorithms). Furthermore, the remaining four categories which mainly explore optimization techniques are reviewed in Part II (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks and metaheuristic search algorithms). For the sake of simplicity, the paper entitled “Machine learning facilitated business intelligence (Part II): Neural networks optimization techniques and applications” is referred to as Part II. This results in a division of 80 articles into 38 and 42 for Part I and Part II, respectively. After discussing the FNN algorithms with their technical merits and limitations, along with real-world management, engineering and health sciences applications for each individual category, the authors suggest seven (three in Part I and other four in Part II) new future directions which can contribute to strengthening the literature.Research limitations/implicationsThe FNN contributions are numerous and cannot be covered in a single study. The authors remain focused on learning algorithms and optimization techniques, along with their application to real-world problems, proposing to improve the generalization performance and convergence rate of FNNs with the characteristics of computing optimal hyperparameters, connection weights, hidden units, selecting an appropriate network architecture rather than trial and error approaches and avoiding overfitting.Practical implicationsThis study will help researchers and practitioners to deeply understand the existing algorithms merits of FNNs with limitations, research gaps, application areas and changes in research studies in the last three decades. Moreover, the user, after having in-depth knowledge by understanding the applications of algorithms in the real world, may apply appropriate FNN algorithms to get optimal results in the shortest possible time, with less effort, for their specific application area problems.Originality/valueThe existing literature surveys are limited in scope due to comparative study of the algorithms, studying algorithms application areas and focusing on specific techniques. This implies that the existing surveys are focused on studying some specific algorithms or their applications (e.g. pruning algorithms, constructive algorithms, etc.). In this work, the authors propose a comprehensive review of different categories, along with their real-world applications, that may affect FNN generalization performance and convergence rate. This makes the classification scheme novel and significant.

This paper examines the escalating challenge of detecting cyber-attacks within Internet of Things (IoT) networks, where conventional security measures often falter in addressing the speed and complexity of contemporary threats. In response to the necessity for more precise, efficient, and adaptive security solutions, we propose a deep learning-based approach that employs feedforward neural networks optimized through the Levenberg-Marquardt algorithm. Our findings indicate that this method markedly surpasses traditional machine learning and deep learning models, such as Support Vector Machines (SVM), Random Forest, and Artificial Neural Network (ANN), achieving an accuracy rate of 99.7%, precision of 99.93%, recall of 99.93%, and an F1-score of 99.93%. Furthermore, the model demonstrates minimal misclassifications and effectively processes substantial data volumes, rendering it highly suitable for the real-time detection of various cyber threats. This system substantially reduces false positive rates and enhances the classification accuracy of different attack types within IoT networks. This research contributes to the advancement of cybersecurity in IoT environments by providing a scalable and robust solution for identifying emerging cyber threats.

CNN is inspired from Primary Visual (V1) neurons. It is a typical deep learning technique and can help teach machine how to see and identify objects. In the most recent decade, deep learning develops rapidly and has been well used in various fields of expertise such as computer vision and natural language processing. As the representative algorithm of deep learning, Convolution Neural Network (CNN) has been regarded as a breakthrough of historic significance in image processing and visual recognition tasks since the astonishing results achieved on ImageNet Large Scale Visual Recognition Competition (ILSVRC) Unlike methods based on handcrafted features, CNN models can build high-level features from low-level ones in a data-driven fashion and have displayed great potential in medical image analysis among the aspects of segmentation of histological images identification, lesion detection, tissue classification, etc. This paper provides a review on CNN from the perspectives of its basic mechanism introduction, structure, typical architecture and main application in medical image analysis through analyzing over 100 references from Google Scholar, PubMed, Web of Science and various sources published from 1958 to 2020.

INTRODUCTION Alzheimer's disease (AD), a leading cause of dementia, requires early detection for effective intervention. This study employs AI to analyze multimodal datasets, including clinical, biomarker, and neuroimaging data, using hybrid deep learning frameworks to improve predictive accuracy. METHODS A novel framework was developed, including trained models for structured data and magnetic resonance images. The structured data model used a long short‐term memory (LSTM) for temporal dependencies and a feedforward neural network (FNN) for static patterns. The MRI‐based model employed ResNet50 and MobileNetV2 to extract spatial features. Models were applied on National Alzheimer's Coordinating Centre (NACC) and Alzheimer's Disease Neuroimaging Initiative (ADNI) datasets and compared to previous works. RESULTS The MRI‐based model achieved 96.19% accuracy on the ADNI dataset, while the hybrid model attained 99.82% accuracy on NACC dataset. DISCUSSION This study highlights hybrid AI models' potential in AD detection, enabling earlier interventions and improved detection outcomes. Highlights AI models were explored for early AD detection using NACC and ADNI datasets. Achieved high accuracy with LSTM on NACC data, showing potential for early AD diagnosis. Evaluated transfer learning models (MobileNetV2, ResNet‐50) to address data limitations. A method is proposed for the careful validation of transfer learning models in medical brain diagnostics.

Purpose In this study, we aimed to develop an automatic atrial fibrillation detection technique for the early prediction of atrial fibrillation, that can be used with wearable devices. Methods An effective deep learning-based technology is proposed to automatically detect atrial fibrillation. First, novel preprocessing algorithms, wavelet transform and sliding window filtering, are introduced to reduce the noise and outliers, respectively, from ECG signals. Then, a robust R-wave detection algorithm is developed. In addition, we proposed a feedforward neural network to detect atrial fibrillation based on ECG records. Results Experiments verified using a tenfold cross-validation strategy showed that the proposed method achieves competitive detection performance, and can be applied to wearable detection devices. The proposed R-wave detection algorithm achieved a detection sensitivity of 99.22%, a positive recognition rate of 98.55%, and a deviance of 2.25% on the MIT-BIH arrhythmia database. The proposed atrial fibrillation detection model achieved an accuracy of 84.00%, a detection sensitivity of 84.26%, a specificity of 93.23%, and an area under the receiver operating curve of 89.40% on a mixed dataset composed of the Challenge2017 database and the MIT-BIH arrhythmia database. Conclusion The analysis demonstrated that the proposed atrial fibrillation detection method could automatically detect atrial fibrillation with high accuracy and efficiency, could be applied to wearable devices, and has great value in the early detection of atrial fibrillation. We believe that our work will make a valuable contribution to the area of atrial fibrillation.

Orthogonal frequency division multiplexing (OFDM) is a promising solution for underwater acoustic communication (UWA); however, it requires careful handling of the challenges of large multipath and severe Doppler effects inherent in underwater acoustic communication. This paper proposes a novel feedforward backpropagated neural network (FBNN) implementation for Doppler scaling estimation using UWA cyclic-prefix (CP) OFDM communication. A two-layered input-output feedforward network is utilized with three different backpropagated training algorithm variants: Fletcher-Reeves Conjugate Gradient (CGF), Polak-Ribiére Conjugate Gradient (CGP), and Conjugate Gradient with Powell/Beale Restarts (CGB). The proposed approach calculates the Doppler scale factor by combining the neural computational power with the accuracies offered by the three training algorithms. To evaluate the effectiveness of the proposed FBNN implementation, root mean square error (RMSE) is used as a performance metric for different multipath and signal-to-noise ratio (SNR) channel conditions. The paper also presents a comparison of the proposed FBNN-based training algorithms’ performance with that of the benchmark offered by conventional methods.