Metaheuristic Optimization-Based Feature Selection for Imagery and Arithmetic Tasks: An fNIRS Study.

In recent decades, the brain-computer interface (BCI) has emerged as a leading area of research. The feature selection is vital to reduce the dataset's dimensionality, increase the computing effectiveness, and enhance the BCI's performance. Using activity-related features leads to a high classification rate among the desired tasks. This study presents a wrapper-based metaheuristic feature selection framework for BCI applications using functional near-infrared spectroscopy (fNIRS). Here, the temporal statistical features (i.e., the mean, slope, maximum, skewness, and kurtosis) were computed from all the available channels to form a training vector. Seven metaheuristic optimization algorithms were tested for their classification performance using a k-nearest neighbor-based cost function: particle swarm optimization, cuckoo search optimization, the firefly algorithm, the bat algorithm, flower pollination optimization, whale optimization, and grey wolf optimization (GWO). The presented approach was validated based on an available online dataset of motor imagery (MI) and mental arithmetic (MA) tasks from 29 healthy subjects. The results showed that the classification accuracy was significantly improved by utilizing the features selected from the metaheuristic optimization algorithms relative to those obtained from the full set of features. All of the abovementioned metaheuristic algorithms improved the classification accuracy and reduced the feature vector size. The GWO yielded the highest average classification rates (p < 0.01) of 94.83 ± 5.5%, 92.57 ± 6.9%, and 85.66 ± 7.3% for the MA, MI, and four-class (left- and right-hand MI, MA, and baseline) tasks, respectively. The presented framework may be helpful in the training phase for selecting the appropriate features for robust fNIRS-based BCI applications.

Brain Tumor/Mass Classification Framework Using Magnetic-Resonance-Imaging-Based Isolated and Developed Transfer Deep-Learning Model.

With the advancement in technology, machine learning can be applied to diagnose the mass/tumor in the brain using magnetic resonance imaging (MRI). This work proposes a novel developed transfer deep-learning model for the early diagnosis of brain tumors into their subclasses, such as pituitary, meningioma, and glioma. First, various layers of isolated convolutional-neural-network (CNN) models are built from scratch to check their performances for brain MRI images. Then, the 22-layer, binary-classification (tumor or no tumor) isolated-CNN model is re-utilized to re-adjust the neurons' weights for classifying brain MRI images into tumor subclasses using the transfer-learning concept. As a result, the developed transfer-learned model has a high accuracy of 95.75% for the MRI images of the same MRI machine. Furthermore, the developed transfer-learned model has also been tested using the brain MRI images of another machine to validate its adaptability, general capability, and reliability for real-time application in the future. The results showed that the proposed model has a high accuracy of 96.89% for an unseen brain MRI dataset. Thus, the proposed deep-learning framework can help doctors and radiologists diagnose brain tumors early.

WBM-DLNets: Wrapper-Based Metaheuristic Deep Learning Networks Feature Optimization for Enhancing Brain Tumor Detection.

This study presents wrapper-based metaheuristic deep learning networks (WBM-DLNets) feature optimization algorithms for brain tumor diagnosis using magnetic resonance imaging. Herein, 16 pretrained deep learning networks are used to compute the features. Eight metaheuristic optimization algorithms, namely, the marine predator algorithm, atom search optimization algorithm (ASOA), Harris hawks optimization algorithm, butterfly optimization algorithm, whale optimization algorithm, grey wolf optimization algorithm (GWOA), bat algorithm, and firefly algorithm, are used to evaluate the classification performance using a support vector machine (SVM)-based cost function. A deep-learning network selection approach is applied to determine the best deep-learning network. Finally, all deep features of the best deep learning networks are concatenated to train the SVM model. The proposed WBM-DLNets approach is validated based on an available online dataset. The results reveal that the classification accuracy is significantly improved by utilizing the features selected using WBM-DLNets relative to those obtained using the full set of deep features. DenseNet-201-GWOA and EfficientNet-b0-ASOA yield the best results, with a classification accuracy of 95.7%. Additionally, the results of the WBM-DLNets approach are compared with those reported in the literature.

A Robust Computer-Aided Automated Brain Tumor Diagnosis Approach Using PSO-ReliefF Optimized Gaussian and Non-Linear Feature Space.

Brain tumors are among the deadliest diseases in the modern world. This study proposes an optimized machine-learning approach for the detection and identification of the type of brain tumor (glioma, meningioma, or pituitary tumor) in brain images recorded using magnetic resonance imaging (MRI). The Gaussian features of the image are extracted using speed-up robust features (SURF), whereas its non-linear features are obtained using KAZE, owing to their high performance against rotation, scaling, and noise problems. To retrieve local-level information, all brain MRI images are segmented into an 8 × 8 pixel grid. To enhance the accuracy and reduce the computational time, the variance-based k-means clustering and PSO-ReliefF algorithms are employed to eliminate the redundant features of the brain MRI images. Finally, the performance of the proposed hybrid optimized feature vector is evaluated using various machine learning classifiers. An accuracy of 96.30% is obtained with 169 features using a support vector machine (SVM). Furthermore, the computational time is also reduced to 1 min compared to the non-optimized features used for training of the SVM. The findings are also compared with previous research, demonstrating that the suggested approach might assist physicians and doctors in the timely detection of brain tumors.

Improved Ablative Properties of Nanodiamond-Reinforced Carbon Fiber-Epoxy Matrix Composites.

The influence of nanodiamonds (NDs) on the thermal and ablative performance of carbon-fiber-reinforced-epoxy matrix compositeswas explored. The ablative response of the composites with 0.2 wt% and 0.4 wt% NDs was studied through pre-and post-burning morphologies of the composite surfaces by evaluation of temperature profiles, weight loss, and erosion rate. Composites containing 0.2 wt% NDs displayed a 10.5% rise in erosion resistance, whereas composites containing 0.4 wt% NDs exhibited a 12.6% enhancement in erosion resistance compared to neat carbon fiber-epoxy composites. A similar trend was witnessed in the thermal conductivity of composites. Incorporation of composites with 0.2 wt% and 0.4 wt% NDs brought about an increase of 37 wt% and 52 wt%, respectively. The current study is valuable for the employment of NDs in carbon fiber composite applications where improved erosion resistance is necessary.

Prediction of the Ultimate Strength of Notched and Unnotched IM7/977-3 Laminated Composites Using a Micromechanics Approach.

This paper proposes a multi-scale analysis technique based on the micromechanics of failure (MMF) to predict and investigate the damage progression and ultimate strength at failure of laminated composites. A lamina's representative volume element (RVE) is developed to predict and calculate constituent stresses. Damages that occurred in the constituents are calculated using separate failure criteria for both fiber and matrix. Subsequently, the volume-based damage homogenization technique is utilized to prevent the localization of damage throughout the total matrix zone. The proposed multiscale analysis procedure is then used to investigate the notched and unnotched behavior of three multi-directional composite layups, [30, 60, 90, -60, 30]2S, [0, 45, 90, -45]2S, and [60, 0, -60]3S, subjected to static tension and compression loading. The specimen is fabricated from unidirectionally reinforced composite (IM7/977-3). The prediction of ultimate strength at failure and equivalent stiffness are then benchmarked against the experimental test data. The comparative analysis with various failure models is also carried out to validate the proposed model. MMF demonstrated the capability to correctly predict the ultimate strength at failure for a range of multidirectional composites laminates under tensile and compressive load. The numerically predicted findings revealed a good agreement with the experimental test data. Out of the three investigated composite layups, the simulated results for the quasi-isotropic [0, 45, 90, -45]2S layup agreed extremely well with the experimental results with all the percentage errors within 10% of the measured failure loads.