An electrically tunable, textile-based metamaterial (MTM) is presented in this work. The proposed MTM unit cell consists of a decagonal-shaped split-ring resonator and a slotted ground plane integrated with RF varactor diodes. The characteristics of the proposed MTM were first studied independently using a single unit cell, prior to different array combinations consisting of 1 × 2, 2 × 1, and 2 × 2 unit cells. Experimental validation was conducted for the fabricated 2 × 2 unit cell array format. The proposed tunable MTM array exhibits tunable left-handed characteristics for both simulation and measurement from 2.71 to 5.51 GHz and provides a tunable transmission coefficient of the MTM. Besides the left-handed properties within the frequency of interest (from 1 to 15 GHz), the proposed MTM also exhibits negative permittivity and permeability from 8.54 to 10.82 GHz and from 10.6 to 13.78 GHz, respectively. The proposed tunable MTM could operate in a dynamic mode using a feedback system for different microwave wearable applications.

In this paper, we report the design and development of a metamaterial (MTM)-based directional coplanar waveguide (CPW)-fed reconfigurable textile antenna using radiofrequency (RF) varactor diodes for microwave breast imaging. Both simulation and measurement results of the proposed MTM-based CPW-fed reconfigurable textile antenna revealed a continuous frequency reconfiguration to a distinct frequency band between 2.42 GHz and 3.2 GHz with a frequency ratio of 2.33:1, and with a static bandwidth at 4–15 GHz. The results also indicated that directional radiation pattern could be produced at the frequency reconfigurable region and the antenna had a peak gain of 7.56 dBi with an average efficiency of more than 67%. The MTM-based reconfigurable antenna was also tested under the deformed condition and analysed in the vicinity of the breast phantom. This microwave imaging system was used to perform simulation and measurement experiments on a custom-fabricated realistic breast phantom with heterogeneous tissue composition with image reconstruction using delay-and-sum (DAS) and delay-multiply-and-sum (DMAS) algorithms. Given that the MWI system was capable of detecting a cancer as small as 10 mm in the breast phantom, we propose that this technique may be used clinically for the detection of breast cancer.

Despite recent technological advances for Photovoltaic panels maintenance (Electroluminescence imaging, drone inspection), only few large-scale studies achieve identification of the precise category of defects or faults. In this work, Electroluminescence imaged modules are automatically split into cells using projections on the x and y axes to detect cell boundaries. Regions containing potential defects or faults are then detected using Hough transform combined with mathematical morphology. Care is taken to remove most of the bus bars or cell boundaries. Afterwards, 25 features are computed, focusing on both the geometry of the regions (e.g. area, perimeter, circularity) and the statistical characteristics of their pixel values (e.g. median, standard deviation, skewness). Finally, features are mapped to the ground truth labels with Support Vector Machine (RBF kernel) and Random Forest algorithms, coupled with undersampling and SMOTE oversampling, with a stratified 5folds approach for cross validation. A dataset of 982 Electroluminescence images of installed multi-crystalline photovoltaic modules was acquired in outdoor conditions (evening) with a CMOS sensor. After automatic blur detection, 753 images or 47244 cells remain to evaluate faults. All images were evaluated by experts in PV fault detection that labelled: Finger failures, and three types of cracks based on their respective severity levels (A, B and C). Our results based on 6 data series, yield using Support Vector Machine an accuracy of 0.997 and a recall of 0.274. Improving the region detection process will most likely allow improving the performance.

Exponential growths of social media and microblogging sites not only provide platforms for empowering freedom of expressions and individual voices, but also enables people to express antisocial be havior like online harassment, cyberbullying, and hate speech. Nu merous works have been proposed to utilize these data for social and antisocial behavior analysis, by predicting the contexts mostly for highlyresourced languages like English. However, some lan guages are underresourced, e.g., South Asian languages like Ben gali, that lack of computational resources for natural language pro cessing (NLP). In this paper 1 , we propose an explainable approach for hate speech detection from underresourced Bengali language, which we called DeepHateExplainer. In our approach, Bengali texts are first comprehensively preprocessed, before classifying them into political, personal, geopolitical, and religious hates, by employing neural ensemble of different transformerbased neural architectures (i.e., monolingual Bangla BERTbase, multilingual BERTcased and un cased, and XLMRoBERTa), followed by identifying important terms with sensitivity analysis and layerwise relevance propagation (LRP) to provide humaninterpretable explanations. Evaluations against several machine learning (linear and treebased models) and deep neural networks (i.e., CNN, BiLSTM, and ConvLSTM with word embeddings) baselines yield F1 scores of 84%, 90%, 88%, and 88%, for political, personal, geopolitical, and religious hates, respectively, during 3fold crossvalidation tests.

In this paper, a compact textile ultrawideband (UWB) planar monopole antenna loaded with a metamaterial unit cell array (MTMUCA) structure with epsilon-negative (ENG) and near-zero refractive index (NZRI) properties is proposed. The proposed MTMUCA was constructed based on a combination of a rectangular- and a nonagonal-shaped unit cell. The size of the antenna was 0.825 λ0 × 0.75 λ0 × 0.075 λ0, whereas each MTMUCA was sized at 0.312λ0 × 0.312λ0, with respect to a free space wavelength of 7.5 GHz. The antenna was fabricated using viscose-wool felt due to its strong metal–polymer adhesion. A naturally available polymer, wool, and a human-made polymer, viscose, that was derived from regenerated cellulose fiber were used in the manufacturing of the adopted viscose-wool felt. The MTMUCA exhibits the characteristics of ENG, with a bandwidth (BW) of 11.68 GHz and an NZRI BW of 8.5 GHz. The MTMUCA was incorporated on the planar monopole to behave as a shunt LC resonator, and its working principles were described using an equivalent circuit. The results indicate a 10 dB impedance fractional bandwidth of 142% (from 2.55 to 15 GHz) in simulations, and 138.84% (from 2.63 to 14.57 GHz) in measurements obtained by the textile UWB antenna. A peak realized gain of 4.84 dBi and 4.4 dBi was achieved in simulations and measurements, respectively. A satisfactory agreement between simulations and experiments was achieved, indicating the potential of the proposed negative index metamaterial-based antenna for microwave applications.