Explore the vast range of titles available.

Brain-Computer Interface (BCI) is an advanced and multidisciplinary active research domain based on neuroscience, signal processing, biomedical sensors, hardware, etc. Since the last decades, several groundbreaking research has been conducted in this domain. Still, no comprehensive review that covers the BCI domain completely has been conducted yet. Hence, a comprehensive overview of the BCI domain is presented in this study. This study covers several applications of BCI and upholds the significance of this domain. Then, each element of BCI systems, including techniques, datasets, feature extraction methods, evaluation measurement matrices, existing BCI algorithms, and classifiers, are explained concisely. In addition, a brief overview of the technologies or hardware, mostly sensors used in BCI, is appended. Finally, the paper investigates several unsolved challenges of the BCI and explains them with possible solutions.

The rise of social media has changed how people view connections. Machine Learning (ML)-based sentiment analysis and news categorization help understand emotions and access news. However, most studies focus on complex models requiring heavy resources and slowing inference times, making deployment difficult in resource-limited environments. In this paper, we process both structured and unstructured data, determining the polarity of text using the TextBlob scheme to determine the sentiment of news headlines. We propose a Stochastic Gradient Descent (SGD)-based Ridge classifier (RC) for blending SGDR with an advanced string processing technique to effectively classify news articles. Additionally, we explore existing supervised and unsupervised ML algorithms to gauge the effectiveness of our SGDR classifier. The scalability and generalization capability of SGD and L2 regularization techniques in RCs to handle overfitting and balance bias and variance provide the proposed SGDR with better classification capability. Experimental results highlight that our string processing pipeline significantly boosts the performance of all ML models. Notably, our ensemble SGDR classifier surpasses all state-of-the-art ML algorithms, achieving an impressive 98.12% accuracy. McNemar’s significance tests reveal that our SGDR classifier achieves a 1% significance level improvement over K-Nearest Neighbor, Decision Tree, and AdaBoost and a 5% significance level improvement over other algorithms. These findings underscore the superior proficiency of linear models in news categorization compared to tree-based and nonlinear counterparts. This study contributes valuable insights into the efficacy of the proposed methodology, elucidating its potential for news categorization and sentiment analysis.

In this article, a novel shaped metamaterial sensor is presented for the recognition of various oils, fluids, and chemicals using microwave frequency. The performance of the designed sensor structure has been studied both theoretically and experimentally, and it works well. A new sample holder for convenient operation is created and located just behind the designed structure. The results of this study performed better than those of prior liquids sensing studies. Various designs were explored using the Genetic Algorithm (GA), and it is embedded in the Computer Simulation Technology (CST) microwave studio, to optimize the optimal dimensions of the resonator. The suggested metamaterial sensor has a good-quality factor and sensitivity in both frequency shifting and amplitude changing. The resonance frequency shifted to 100 MHz between olive and corn oils, 70 MHz between sunflower and palm oils, 80 MHz between clean and waste brake fluids, and 90 MHz between benzene and carbon-tetrachloride chemicals. The quality factor of the sensor is 135, sensitivity is 0.56, and the figure of merit is 76 which expresses its efficient performance. Furthermore, the proposed sensor can sensitively distinguish different liquids by using the frequency shifting property. The study was carried out in three stages: dielectric constant (DK) measurement with the N1500A dielectric measurement kit, simulation of the structure, and experimental test study with the vector network analyzer. Since the recommended sensor has high sensitivity, good quality factor, and excellent performance, hence it can be used in chemical, oil, and microfluidic industries for detecting various liquid samples.

This paper represents a penta band square enclosed star-shaped modified split ring resonator (SRR) based single negative meta-atom absorber (MAA) for multi-band microwave regime applications. FR-4 low-cost material has been used as a substrate to make the MAA unit cell with 0.101λ 0  × 0.101λ 0 of electrical size, where λ 0 is the wavelength calculated at the lower resonance frequency of 3.80 GHz. There are two outer square split ring and one inner star ring shape resonator of 0.035 mm thickness of copper placed on the one side, and another side of the substrate has full copper to construct the desired unit cell. The MAA unit cell provides five absorption peaks of 97.87%, 93.65%, 92.66%, 99.95%, and 99.86% at the frequencies of 3.80, 5.65, 8.45, 10.82, and 15.92 GHz, respectively, which covers S-, C-, X-, and Ku- bands. The properties of MAA have been investigated and analyzed in the E-, H-fields and surface current. The EMR and highest Q factor of the designed MAA is 9.87 and 30.41, respectively, and it shows a single negative (SNG) property. Different types of parametric analysis have been done to show the better performance of absorption. Advanced Designed System (ADS) software has been used for equivalent circuit to verify the simulated S 11 result obtained from the CST-2019 software. Experimental outcomes of the MAA unit cell have a good deal with the simulated result and measured result of the 24 × 20 array of unit cells also shown. Since the unit cell provides superior EMR, excellent Q-factor, and highest absorption so the recommended MAA can be effectively used as a penta band absorber in microwave applications, like notch filtering, sensing, reducing the unintended noise generated with the copper component of the satellite and radar antennas.

The absence of electricity is among the gravest problems preventing a nation’s development. Hybrid renewable energy systems (HRES) play a vital role to reducing this issue. The major goal of this study is to use the non-dominated sorting genetic algorithm (NSGA)-II and hybrid optimization of multiple energy resources (HOMER) Pro Software to reduce the net present cost (NPC), cost of energy (COE), and CO2 emissions of proposed power system. Five cases have been considered to understand the optimal HRES system for Kutubdia Island in Bangladesh and analyzed the technical viability and economic potential of this system. To demonstrate the efficacy of the suggested strategy, the best case outcomes from the two approaches are compared. The study’s optimal solution is also subjected to a sensitivity analysis to take into account fluctuations in the annual wind speed, solar radiation, and fuel costs. According to the data, the optimized PV/Wind/Battery/DG system (USD 711,943) has a lower NPC than the other cases. The NPC obtained by the NSGA-II technique is 2.69% lower than that of the HOMER-based system.

In this research paper, an inverse double V loaded complementary square split ring resonator based double negative (DNG) metamaterial has been developed and examined numerically and experimentally. The electromagnetic (EM) properties of the proposed inverse double V-structure were calculated using computer simulation technology (CST-2019) and the finite integration technique (FIT). The designed metamaterial provides three resonance frequencies are 2.86, 5, and 8.30 GHz, covering S-, C-, and X-bands. The total size of the recommended unit cell is 8 × 8 × 1.524 mm 3 , and a high effective medium ratio (EMR) value of 13.11 was found from it. The − 10 dB bandwidths of this structure are 2.80 to 2.91, 4.76 to 5.17, and 8.05 to 8.42 GHz. The proposed structure's novelty is its small size, simple resonator structure, which provides double negative characteristics, high EMR, maximum coverage band, and required resonance frequencies. Wi-Fi network speeds are generally faster when frequencies in the 5 GHz band are used. Since the proposed structure provides a 5 GHz frequency band, hence the suggested metamaterial can be used in Wi-Fi for high bandwidth and high-speed applications. The marine radars operate in X-band, and weather radar works in S-band. Since the designed cell provides two more resonance frequencies, i.e., 2.86 GHz (S-band) and 8.30 GHz (X-band), the proposed metamaterial could be used in weather radar and marine radar. The design process and various parametric studies have been analyzed in this article. The equivalent circuit is authenticated using the advanced design system (ADS) software compared with CST simulated result. The surface current, E-field, and H-field distributions have also been analyzed. Different types of array structure, i.e., 1 × 2, 2 × 2, 3 × 3, 4 × 4, and 20 × 25 is examined and validated by the measured result. The simulated and measured outcome is an excellent agreement for the inverse double V loaded CSSRR unit cell and array. We showed the overall performance of the suggested structure is better than the other structures mentioned in the paper. Since the recommended metamaterial unit cell size is small, provides desired resonance frequency, gives a large frequency band and high EMR value; hence the suggested metamaterial can be highly applicable for Radar and Wi-Fi.

Human Activity Recognition (HAR), alongside Ambient Assisted Living (AAL), are integral components of smart homes, sports, surveillance, and investigation activities. To recognize daily activities, researchers are focusing on lightweight, cost-effective, wearable sensor-based technologies as traditional vision-based technologies lack elderly privacy, a fundamental right of every human. However, it is challenging to extract potential features from 1D multi-sensor data. Thus, this research focuses on extracting distinguishable patterns and deep features from spectral images by time-frequency-domain analysis of 1D multi-sensor data. Wearable sensor data, particularly accelerator and gyroscope data, act as input signals of different daily activities, and provide potential information using time-frequency analysis. This potential time series information is mapped into spectral images through a process called use of ’scalograms’, derived from the continuous wavelet transform. The deep activity features are extracted from the activity image using deep learning models such as CNN, MobileNetV3, ResNet, and GoogleNet and subsequently classified using a conventional classifier. To validate the proposed model, SisFall and PAMAP2 benchmark datasets are used. Based on the experimental results, this proposed model shows the optimal performance for activity recognition obtaining an accuracy of 98.4% for SisFall and 98.1% for PAMAP2, using Morlet as the mother wavelet with ResNet-101 and a softmax classifier, and outperforms state-of-the-art algorithms.

Neurological disorders (NDs) are becoming more common, posing a concern to pregnant women, parents, healthy infants, and children. Neurological disorders arise in a wide variety of forms, each with its own set of origins, complications, and results. In recent years, the intricacy of brain functionalities has received a better understanding due to neuroimaging modalities, such as magnetic resonance imaging (MRI), magnetoencephalography (MEG), and positron emission tomography (PET), etc. With high-performance computational tools and various machine learning (ML) and deep learning (DL) methods, these modalities have discovered exciting possibilities for identifying and diagnosing neurological disorders. This study follows a computer-aided diagnosis methodology, leading to an overview of pre-processing and feature extraction techniques. The performance of existing ML and DL approaches for detecting NDs is critically reviewed and compared in this article. A comprehensive portion of this study also shows various modalities and disease-specified datasets that detect and records images, signals, and speeches, etc. Limited related works are also summarized on NDs, as this domain has significantly fewer works focused on disease and detection criteria. Some of the standard evaluation metrics are also presented in this study for better result analysis and comparison. This research has also been outlined in a consistent workflow. At the conclusion, a mandatory discussion section has been included to elaborate on open research challenges and directions for future work in this emerging field.

The progress in hyperspectral image (HSI) classification owes much to the integration of various deep learning techniques. However, the inherent 3D cube structure of HSIs presents a unique challenge, necessitating an innovative approach for the efficient utilization of spectral data in classification tasks. This research focuses on HSI classification through the adoption of a recently validated deep-learning methodology. Challenges in HSI classification encompass issues related to dimensionality, data redundancy, and computational expenses, with CNN-based methods prevailing due to architectural limitations. In response to these challenges, we introduce a groundbreaking model known as “Crossover Dimensionality Reduction and Multi-branch Deep Learning” (CMD) for hyperspectral image classification. The CMD model employs a multi-branch deep learning architecture incorporating Factor Analysis and MNF for crossover feature extraction, with the selection of optimal features from each technique. Experimental findings underscore the CMD model’s superiority over existing methods, emphasizing its potential to enhance HSI classification outcomes. Notably, the CMD model exhibits exceptional performance on benchmark datasets such as Salinas Scene (SC), Pavia University (PU), Kennedy Space Center (KSC), and Indian Pines (IP), achieving impressive overall accuracy rates of 99.35% and 99.18% using only 5% of the training data.

This study offers a compact size, highly sensitive, and reliable split ring resonator-based sensor for microwave sensing applications. The designed unit cell is assembled on a 1.575 mm width of low-cost dielectric substrate Rogers RT5880. CST software is employed to design and analyze the proposed sensor. The size of the sensor is 8 8 mm 2 which is very small and it’s a low price. Also, the CST-simulated model was validated using ADS software. The MATLAB is used to extract the effective parameters of the suggested unit cell. Then the prototype is fabricated, and the laboratory measurements are done to validate the simulated results. The obtained resonances from the designed sensor are 2.77, 5.78, 9.82, and 12.29 GHz. Sensing performance is examined by using various materials and thicknesses of FR-4 material. After analysis, the sensor’s EMR, quality factor, and figure of merit (FoM) are found to be 13.54, 325, and 6.15 respectively which are effective. The sensitivity of the sensor is 12.03% which means the sensor performance is optimum. The resonances are shifted to 210, 600, and 810 MHz due to permittivity change and 290, 270, and 560 MHz due to materials thickness change. All laboratory results are perfectly matched with the simulated results. Due to its small size, low cost, high sensitivity, and superior performance, the suggested sensor can be used for sensing material thickness as well as glass, plastic, and substrate materials.