Final Layer Research Articles

Microvascular Endothelial Glycocalyx Surface Layer Visualization and Quantification.

As a primary interface between the blood and underlying vascular wall, the endothelial glycocalyx layer is common to all blood vessels and covers the luminal surface of all endothelial cells. The endothelial glycocalyx has important roles as a regulator of microvascular endothelial functions such as mechanotransduction, leukocyte adhesion, and microvascular permeability. Disruption of the molecular structure of the endothelial glycocalyx disturbs physiological, and hemodynamic processes associated with the microvascular wall leads to microvascular hyperpermeability. Studying the glycocalyx is challenging because cultured cells present aberrant glycocalyx structure and tissue fixation techniques lead to the degradation and loss of this fine and delicate layer. Therefore, studying the glycocalyx requires in vivo imaging of the microcirculation. Here we describe two techniques for direct imaging and assessment of the glycocalyx surface layer integrity using intravital microscopy (IVM), a method widely used in the study of the dynamic changes that occur in the microcirculation during inflammation or injury.

Interpretability of a Deep Learning-Based Prediction Model for Mandibular Osteoradionecrosis.

The development of radiation-induced toxicities is a multifactorial process. Existing DVH-based prediction models use traditional multivariate analysis to combine all the potential risk factors. Recently, deep learning (DL) has been proposed for predicting mandibular osteoradionecrosis (ORN) directly from 3D dose distribution maps [1]. However, with this approach, incorporating non-imaging data such as potential risk factors presents challenges. We investigate the use of DL-based multimodality fusion for the purpose of radiation-induced ORN toxicity prediction. This study explores early and late fusion strategies for combining 3D radiation dose distribution maps and clinical and demographic variables in the prediction of mandibular ORN incidence in head and neck cancer patients treated with radiotherapy. The results are compared to single-modality predictions with a random forest (RF) trained only on clinical variables and a 3D DenseNet40 trained on dose maps alone. We investigate two different fusion approaches. In the first, the image features extracted from the radiation dose maps using a 3D DenseNet40 were concatenated with the clinical variables into one single vector using a type II early fusion strategy. The combined feature vector was input into a fully connected layer for classification of ORN vs. controls. A final softmax activation layer was added to obtain the class predicted probabilities. The second approach used a late fusion strategy, in which the outputs from the 3D DenseNet40 and the RF model were combined by averaging the predicted classification probabilities for each of the two classes (ORN and no ORN) to obtain the final class decision on a case-by-case basis. The AUROC values obtained for the late and early fusion models and the single-modality 3D DenseNet40 and RF models were 0.70, 0.68, 0.69 and 0.60, respectively. The highest AUC ROC was observed with the late fusion approach, which was statistically significantly different to that of the RF single-modality model with a significance level of 0.05. However, after Bonferroni correction (Altman 1999) for multiple comparisons was applied, resulting in a corrected significance level of 0.05/6 = 0.008 for each comparison, no statistically significant difference was observed between any of the models' AUROC values. This is most likely due to the lack of discriminative contribution observed from clinical variables, which on their own resulted in a poorly predictive RF model. To our knowledge, no previous work has been published on the use of multimodal fusion DL methods to combine dose distribution maps and clinical variables in the prediction of mandibular ORN. Although non-conclusive results were obtained, this study demonstrates the potential of DL in the prediction of the multifactorial side effects resulting from radiotherapy treatments. [1] Humbert-Vidan L et al. Prediction of Mandibular ORN Incidence from 3D Radiation Dose Distribution Maps Using DL (2022).

Hierarchical One-Class Model With Subnetwork for Representation Learning and Outlier Detection.

The multilayer one-class classification (OCC) frameworks have gained great traction in research on anomaly and outlier detection. However, most multilayer OCC algorithms suffer from loosely connected feature coding, affecting the ability of generated latent space to properly generate a highly discriminative representation between object classes. To alleviate this deficiency, two novel OCC frameworks, namely: 1) OCC structure using the subnetwork neural network (OC-SNN) and 2) maximum correntropy-based OC-SNN (MCOC-SNN), are proposed in this article. The novelties of this article are as follows: 1) the subnetwork is used to build the discriminative latent space; 2) the proposed models are one-step learning networks, instead of stacking feature learning blocks and final classification layer to recognize the input pattern; 3) unlike existing works which utilize mean square error (MSE) to learn low-dimensional features, the MCOC-SNN uses maximum correntropy criterion (MCC) for discriminative feature encoding; and 4) a brand-new OCC dataset, called CO-Mask, is built for this research. Experimental results on the visual classification domain with a varying number of training samples from 6131 to 513 061 demonstrate that the proposed OC-SNN and MCOC-SNN achieve superior performance compared to the existing multilayer OCC models. For reproducibility, the source codes are available at https://github.com/W1AE/OCC.

Surgical phase classification and operative skill assessment through spatial context aware CNNs and time-invariant feature extracting autoencoders

Automated surgical video analysis promises improved healthcare. We propose novel spatial context aware combined loss function for end-to-end Encoder-Decoder training for Surgical Phase Classification (SPC) on laparoscopic cholecystectomy (LC) videos. Proposed loss function leverages on fine-grained class activation maps obtained from fused multi-layer Layer-CAM for supervised learning of SPC, obtaining improved Layer-CAM explanations. Post classification, we introduce graph theory to incorporate known hierarchies of surgical phases. We report peak SPC accuracy of 96.16%, precision of 94.08% and recall of 90.02% on public dataset Cholec80, with 7 phases. Our proposed method utilizes just 73.5% of parameters as against existing state-of-the-art methodology, achieving improvement of 0.5% in accuracy, 1.76% in precision with comparable recall, with an order less standard deviation. We also propose DNN based surgical skill assessment methodology. This approach utilizes surgical phase prediction scores from the final fully-connected layer of spatial-context aware classifier to form multi-channel temporal signal of surgical phases. Time-invariant representation is obtained from this temporal signal through time- and frequency-domain analyses. Autoencoder based time-invariant features are utilized for reconstruction and identification of prominent peaks in dissimilarity curves. We devise a surgical skill measure (SSM) based on spatial-context aware temporal-prominence-of-peaks curve. SSM values are expected to be high when executed skillfully, aligning with expert assessed GOALS metric. We illustrate this trend on Cholec80 and m2cai16-tool datasets, in comparison with GOALS metric. Concurrence in the trend of SSM with respect to GOALS metric is obtained on these test videos, making it a promising step towards automated surgical skill assessment.

Key information-guided networks for medical image segmentation in medical systems

Motivated by the goals of overcoming inherent engineering difficulties on segmentation accuracy arising from low contrast and complex tissue relationships in medical images, this paper investigates how key information can be extracted and analyzed in a targeted manner to discover relationships between tissues and enhance feature differentiation. It proposes the Key Information-guided segmentation algorithm, which consists of two key components: the Key Region-guided Sparse Self-Attention (KRSSA) module and the Hard Pixels Multisubclass Contrast learning (HPMCL) module. The former is applied in the encoder by activating the importance of global features and adaptively selecting attentional regions. Experimental results show that propagating large amounts of complex and redundant information suppresses learning. The latter is applied in the final decision layer, where the feature space of each class is partitioned into several subclasses, and hard pixels are continuously pulled towards the closest subclass of their respective class, away from all subclasses of other classes by contrastive learning. Experimental results show that moving pixels towards subclasses rather than a single class center leads to more effective segmentation results. In summary, we propose a novel visual model and extensively validate it on the Brain Tumor Segmentation 2019 Challenge (BraTS2019) dataset, BraTS2020 dataset, and the Medical Segmentation Decathlon (MSD) dataset, namely in brain tumors and the hippocampus. The Dice similarity coefficients of 0.806, 0.904, and 0.853 for the enhanced tumor, whole tumor, and tumor core, respectively, in the Brats2020 validation set ranked fourth out of 345 participating methods. This method has significant implications for addressing challenges in medical image segmentation, including low attention to key regions, class imbalance, and background interference.

Chagas parasite classification in blood sample images using different machine learning architectures.

Chagas disease is a life-threatening illness mainly found in Latin America. Early identification and diagnosis of Chagas disease are critical for reducing the death rate of individuals since cures and treatments are available at the acute stage. In this work, we test and compare several deep learning classification models on smear blood sample images for the task of Chagas parasite classification. Our experiments showed that the best classification model is a deep learning architecture based on a residual network together with separable convolution blocks as feature extractors and using a support vector machine algorithm as the classifier in the final layer. This optimized model, we named Res2_SVM, with a reduced number of parameters, achieved an accuracy of [Formula: see text], precision of [Formula: see text], recall of [Formula: see text], and F1-score of [Formula: see text] on our test dataset, overcoming other machine learning models.

Cascading AB‐YOLOv5 and PB‐YOLOv5 for rib fracture detection in frontal and oblique chest X‐ray images

AbstractConvolutional deep learning models have shown comparable performance to radiologists in detecting and classifying thoracic diseases. However, research on rib fractures remains limited compared to other thoracic abnormalities. Moreover, existing deep learning models primarily focus on using frontal chest X‐ray (CXR) images. To address these gaps, the authors utilised the EDARib‐CXR dataset, comprising 369 frontal and 829 oblique CXRs. These X‐rays were annotated by experienced radiologists, specifically identifying the presence of rib fractures using bounding‐box‐level annotations. The authors introduce two detection models, AB‐YOLOv5 and PB‐YOLOv5, and train and evaluate them on the EDARib‐CXR dataset. AB‐YOLOv5 is a modified YOLOv5 network that incorporates an auxiliary branch to enhance the resolution of feature maps in the final convolutional network layer. On the other hand, PB‐YOLOv5 maintains the same structure as the original YOLOv5 but employs image patches during training to preserve features of small objects in downsampled images. Furthermore, the authors propose a novel two‐level cascaded architecture that integrates both AB‐YOLOv5 and PB‐YOLOv5 detection models. This structure demonstrates improved metrics on the test set, achieving an AP30 score of 0.785. Consequently, the study successfully develops deep learning‐based detectors capable of identifying and localising fractured ribs in both frontal and oblique CXR images.

Hybrid Deep Neural Network Framework Combining Skeleton and Gait Features for Pathological Gait Recognition.

Human skeleton data obtained using a depth camera have been used for pathological gait recognition to support doctor or physician diagnosis decisions. Most studies for skeleton-based pathological gait recognition have used either raw skeleton sequences directly or gait features, such as gait parameters and joint angles, extracted from raw skeleton sequences. We hypothesize that using skeleton, joint angles, and gait parameters together can improve recognition performance. This study aims to develop a deep neural network model that effectively combines different types of input data. We propose a hybrid deep neural network framework composed of a graph convolutional network, recurrent neural network, and artificial neural network to effectively encode skeleton sequences, joint angle sequences, and gait parameters, respectively. The features extracted from three different input data types are fused and fed into the final classification layer. We evaluate the proposed model on two different skeleton datasets (a simulated pathological gait dataset and a vestibular disorder gait dataset) that were collected using an Azure Kinect. The proposed model, with multiple types of input, improved the pathological gait recognition performance compared to single input models on both datasets. Furthermore, it achieved the best performance among the state-of-the-art models for skeleton-based action recognition.

Vacuum Deposited Perovskites with a Controllable Crystal Orientation.

The preferential orientation of the perovskite (PVK) is typically accomplished by manipulation of the mixed cation/halide composition of the solution used for wet processing. However, for PVKs grown by thermal evaporation, this has been rarely addressed. It is unclear how variation in crystal orientation affects the optoelectronic properties of thermally evaporated films, including the charge carrier mobility, lifetime, and trap densities. In this study, we use different intermediate annealing temperatures Tinter between two sequential evaporation cycles to control the Cs0.15FA0.85PbI2.85Br0.15 orientation of the final PVK layer. XRD and 2D-XRD measurements reveal that when using no intermediate annealing primarily the (110) orientation is obtained, while when using Tinter = 100 °C a nearly isotropic orientation is found. Most interestingly for Tinter > 130 °C a highly oriented PVK (100) is formed. We found that although bulk electronic properties like photoconductivity are independent of the preferential orientation, surface related properties differ substantially. The highly oriented PVK (100) exhibits improved photoluminescence in terms of yield and lifetime. In addition, high spatial resolution mappings of the contact potential difference (CPD) as measured by KPFM for the highly oriented PVK show a more homogeneous surface potential distribution than those of the nonoriented PVK. These observations suggest that a highly oriented growth of thermally evaporated PVK is preferred to improve the charge extraction at the device level.

Preparation and characterization of high catalytic performance supported TS-2 zeolites for phenol hydroxylation

Good inter-grown TS-2 zeolites layer is successfully prepared on the outer surface of porous millimeter α-Al2O3 sphere by secondary hydrothermal synthesis. The supported TS-2 zeolites are loaded into a fixed-bed catalytic reactor for catalyzing phenol hydroxylation by hydrogen peroxide, which could efficiently avoid the fussy separation process. Influences of synthesis parameters on Ti active micro-environment, crystal morphology and catalytic performance of the supported TS-2 zeolites are investigated in this work, medium isopropanol content is necessary for preparing fine and homogenous TS-2 zeolites layer on the porous α-Al2O3 sphere. Besides, formation process of the supported TS-2 zeolites is studied in this study, which divided into three stages, dissolution of seed crystals, formation of novel nuclei, growth and aggregation of TS-2 zeolites layer. When the titanium source, isopropanol/SiO2 and TiO2/SiO2 molar ratio of the initial synthesis gel are tetrabutyl titanate, 1.0 and 0.035, tetra-coordinated titanium containing and compact TS-2 zeolites layer are fully covered on the α-Al2O3 sphere, the optimum phenol conversion and dihydroxybenzene selectivity of the zeolites are 40.07% and 98.52% at 65 °C.

A vision transformer for fine-grained classification by reducing noise and enhancing discriminative information

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC). These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC tasks. However, there are some limitations when applying ViT directly to FGVC. First, ViT needs to split images into patches and calculate the attention of every pair, which may result in heavy noise calculation during the training phase and unsatisfying performance when handling fine-grained images with complex backgrounds and small objects. Second, complementary information is important for FGVC, but a standard ViT works by using the class token in the final layer for classification which is not enough to extract comprehensive fine-grained information at different levels. Third, the class token fuses the information of all patches in the same manner, in other words, the class token treats each patch equally. However, the discriminative parts should be more critical. To address these issues, we propose ACC-ViT including three novel components, i.e., Attention Patch Combination (APC), Critical Regions Filter (CRF), and Complementary Tokens Integration (CTI). Thereinto, APC pieces informative patches from two images to generate a new image to mitigate the noisy calculation and reinforce the differences between images. CRF emphasizes tokens corresponding to discriminative regions to generate a new class token for subtle feature learning. To extract comprehensive information, CTI integrates complementary information captured by class tokens in different ViT layers. We conduct comprehensive experiments on four widely used datasets and the results demonstrate that ACC-ViT can achieve competitive performance. The source code is available at https://github.com/Hector0426/fine-grained-image-classification-with-vit.

Intelligent ADL Recognition via IoT-Based Multimodal Deep Learning Framework.

Smart home monitoring systems via internet of things (IoT) are required for taking care of elders at home. They provide the flexibility of monitoring elders remotely for their families and caregivers. Activities of daily living are an efficient way to effectively monitor elderly people at home and patients at caregiving facilities. The monitoring of such actions depends largely on IoT-based devices, either wireless or installed at different places. This paper proposes an effective and robust layered architecture using multisensory devices to recognize the activities of daily living from anywhere. Multimodality refers to the sensory devices of multiple types working together to achieve the objective of remote monitoring. Therefore, the proposed multimodal-based approach includes IoT devices, such as wearable inertial sensors and videos recorded during daily routines, fused together. The data from these multi-sensors have to be processed through a pre-processing layer through different stages, such as data filtration, segmentation, landmark detection, and 2D stick model. In next layer called the features processing, we have extracted, fused, and optimized different features from multimodal sensors. The final layer, called classification, has been utilized to recognize the activities of daily living via a deep learning technique known as convolutional neural network. It is observed from the proposed IoT-based multimodal layered system's results that an acceptable mean accuracy rate of 84.14% has been achieved.

Evaluation of Supramolecular Gel Properties and Its Application in Drilling Fluid Plugging

Supramolecular gels are physically cross-linked hydrogels formed by non-covalent interactions. The synthesis, structure optimization, property regulation, and application expansion of supramolecular gels has gradually become the research hotspot in the field of gel materials. According to the non-covalent interactions such as hydrophobic association and hydrogen bonding, the supramolecular gel prepared in this study has excellent rheological properties and adaptive filling and plugging properties, and can be used in the field of drilling fluid plugging. In this paper, the microstructure, rheological properties, temperature resistance, and plugging properties of supramolecular gels were studied and characterized in detail. The experimental findings demonstrated that when the strain was less than 10%, the supramolecular gel displayed an excellent linear viscoelastic region. The increase in strain weakens the rheological properties of supramolecular gel and reduces the elastic modulus of supramolecular gel to a certain extent. The supramolecular gel still had a neat three-dimensional reticular structure after curing at high temperatures, and the network of each layer was closely connected. Its extensibility and tensile properties were good, and it had excellent temperature resistance and mechanical strength. The supramolecular gel had excellent tensile and compressive properties and good deformation recovery properties. When the elongation of the supramolecular gel reached 300%, the tensile stress was 2.33 MPa. When the compression ratio of supramolecular gel was 91.2%, the compressive stress could reach 4.78 MPa. The supramolecular gel could show an excellent plugging effect on complex loss layers with different fracture pore sizes, the plugging success rate could reach more than 90%, and the plugging layer could withstand 6.3 MPa external pressure. The smart plugging fluid prepared with supramolecular gel material could quickly form a fine barrier layer on the rock surface of the reservoir. It could effectively isolate drilling fluid from entering the reservoir and reduce the adverse effects, such as permeability reduction caused by drilling fluid entering the reservoir, so as to achieve the purpose of reservoir protection.

Aspect-based Text Classification for Sentimental Analysis using Attention mechanism with RU-BiLSTM

Sentiment analysis has gained increasing attention from an educational and social perspective with the huge expansion of user interactions due to the Web’s significant improvement. The connection between an opinion target’s polarity scores and other aspects of the content is defined by aspect-based sentiment analysis. Identifying aspects and determining their different polarities is quite complicated because they are frequently implicit. To overcome these difficulties, efficient hybrid methods are used in aspect-based text classification in sentiment analysis. The existing process evaluates the aspects of polarity by using a Convolutional neural network, and it does not work with Big data. In this work, aspect-based text classification and attention mechanisms are used to assist in filtering out irrelevant information and quickly locating the essential features in big data. Initially, the data is collected, and then the data is preprocessed by using Tokenization, Stop word removal, Stemming, and Lemmatization. After preprocessing, the features are vectorized and extracted using Bag-of-Words and TF-IDF. Then, the extracted features are given into word embeddings by GloVe and Word2vec. It uses Deep Recurrent based Bidirectional Long Short Term Memory (RUBiLSTM) for aspect-based sentiment analysis. The RU-Bi-LSTM method integrates aspect-based embeddings and an attention mechanism for text classification. The attention mechanism focuses on more crucial aspects and the bidirectional LSTM to maintain context in both ways. Finally, the binary and ternary classification outcomes are obtained using the final dense softmax output layer. The proposed RU-BiLSTM uses four reviews and two Twitter datasets. The results of the studies demonstrate the efficacy of the RU-BiLSTM model, which outperformed aspect-based classifications on lengthy reviews and short tweets in terms of evaluation.

Optimizing Hyperspectral Imaging Classification Performance with CNN and Batch Normalization

Background: Hyperspectral imaging systems face numerous challenges in acquiring accurate spatial-spectral hypercubes due to sample surface heterogeneity, environmental instability, and instrumental noise. Preprocessing strategies such as outlier detection, calibration, smoothing, and normalization are typically employed to address these issues, selecting appropriate techniques based on prediction performance evaluation. However, the risk of misusing inappropriate preprocessing methods remains a concern. Methods: In this study, we evaluate the impact of five normalization methods on the classification performance of six different classifiers using honey hyperspectral images. Our results show that different classifiers have varying compatible normalization techniques and that using Batch Normalization with Convolutional Neural Networks (CNN) can significantly improve classification performance and diminish the variations among other normalization techniques. The CNN with Batch Normalization can achieve a macro average F1 score of ≥0.99 with four different normalization methods and ≥0.97 without normalization. Furthermore, we analyze kernel weights' distribution in the CNN models' final convolutional layers using statistical measurements and kernel density estimation (KDE) graphs. Results: We find that the performance improvements resulting from adding BatchNorm layers are associated with kernel weight range, kurtosis, and density around 0. However, the differences among normalization methods do not show a strong correlation with kernel weight distribution. In conclusion, our findings demonstrate that the CNN with Batch Normalization layers can achieve better prediction results and avoid the risk of inappropriate normalization.

An amalgamation of vision transformer with convolutional neural network for automatic lung tumor segmentation.

Lung cancer has the highest mortality rate. Its diagnosis and treatment analysis depends upon the accurate segmentation of the tumor. It becomes tedious if done manually as radiologists are overburdened with numerous medical imaging tests due to the increase in cancer patients and the COVID pandemic. Automatic segmentation techniques play an essential role in assisting medical experts. The segmentation approaches based on convolutional neural networks have provided state-of-the-art performances. However, they cannot capture long-range relations due to the region-based convolutional operator. Vision Transformers can resolve this issue by capturing global multi-contextual features. To explore this advantageous feature of the vision transformer, we propose an approach for lung tumor segmentation using an amalgamation of the vision transformer and convolutional neural network. We design the network as an encoder-decoder structure with convolution blocks deployed in the initial layers of the encoder to capture the features carrying essential information and the corresponding blocks in the final layers of the decoder. The deeper layers utilize the transformer blocks with a self-attention mechanism to capture more detailed global feature maps. We use a recently proposed unified loss function that combines cross-entropy and dice-based losses for network optimization. We trained our network on a publicly available NSCLC-Radiomics dataset and tested its generalizability on our dataset collected from a local hospital. We could achieve average dice coefficients of 0.7468 and 0.6847 and Hausdorff distances of 15.336 and 17.435 on public and local test data, respectively.

The influence of surface morphology of the as-fabricated layer on the molten pool flow behavior during the forming process of the next layer for laser powder bed fusion

The surface morphology is essential for the fabricated quality of Laser powder bed fusion (LPBF) additive manufacturing. There is a trend that more and more researchers are an attempt to improve surface quality unlimited. However, besides the final layer for the fabricated products, which directly affects the performance and user experience, does the surface morphology of the as-fabricated layer have an altogether positive effect on the forming process of the next layer? Furthermore, does it need to improve the surface quality unlimited? In this research, three kinds of typical surface morphology, flat surface, balling surface, and periodic rough surface, were analyzed and simplified. Then a fluid-heat coupling numerical model was built considering the surface morphology of the as-fabricated layer. The flow behavior of the molten pool during the forming process of the next layer under different kinds of surface morphology of the as-fabricated layer was investigated. The results indicate that achieving an excessively high-quality surface morphology is needless, and an appropriate periodic rough surface is beneficial to improve the forming quality.

The influence of thermomechanical treatment pathways on texture and mechanical properties in ARB Cu/Nb nanolaminates

Accumulative roll-bonded Cu/Nb nanolaminates (ARB Cu/Nb) possess high strength, thermal stability, and radiation tolerance arising from a high content of heterophase interfaces at fine layer thicknesses. These properties can be tailored by processing parameters used in the ARB Cu/Nb fabrication process, in which layer thickness, thermal history, and strain pathway determine the interface types and resultant properties found in the material. In this work, we subject ARB Cu/Nb to annealing, and then two different rolling pathways – one where rolling direction is held constant (longitudinal rolling, or LR), and one where rolling direction is rotated by 90° and held constant thereafter (cross rolling, or CR). Rolling is performed on ARB Cu/Nb over a targeted range of layer thicknesses from 193 to 25 nm and resultant bulk textures measured by neutron diffraction are correlated with mechanical properties measured by miniaturized tensile tests. The annealing procedure sharpens texture in both phases. We find that Cu mostly develops the same texture in LR and CR. In contrast, Nb develops a distinct texture along the CR pathway that is distinct from the LR texture. The composite texture of Cu/Nb is thus distinct between LR and CR pathways. This difference in texture development between Cu and Nb as a function of strain after change in rolling direction demonstrates the viability for deliberate pairing of Cu LR and Nb CR textures at a desired layer thickness. For mechanical properties, we find that differences in texture do not result in yield or flow stress differences above a layer thickness of 25 nm. Below a layer thickness of 25 nm, despite similar Taylor factors, yield and flow stress and are significantly different. This indicates texture only influences mechanical behavior at low layer thickness, where interface structure dominates mechanical properties.

Comparison of Solidification Microstructure Evolution of Al-10Si and Recycled Aluminium Beverage Can Strips Made in a Strip Caster

A strip caster was used to cast two types of aluminium alloys: an almost eutectic Al-Si alloy (Al 10 Si) with contaminants of 0.6 Fe, 0.2 Pb, and 1.4 Sn, which exhibits a polyphase microstructure upon solidification, and recycled aluminium beverage cans made from Al 0.8 Mn alloy containing 0.4 Si, 0.5 Fe, and 0.1 Mg, which has a monophase microstructure upon solidification. The molten materials were poured at 650 oC (Al 10 Si) and 670 oC (Al 0.8 Mn, 0.4 Si, 0.5 Fe, 0.1 Mg) on a cooling slope specially designed to obtain a semisolid material. This semisolid material was then dragged between rolls at a rate of 0.2 m/s to obtain high-quality metal strips. There was less eutectic modification with larger Al-α grains in the middle region of the sheet between the fine eutectic layers, indicating a lower cooling rate. However, during the recycling of aluminium beverage cans, large grains were formed with a columnar structure at the interface of the rolls, and semisolid melts with cracks were formed between the columnar grain boundaries owing to the compression of the rolls. The middle of these grains contained smaller equiaxial grains that were subjected to dragging. The as-cast specimens were submitted to homogenisation heat treatment at 560 oC for a period of 10 h and cooled to room temperature before being cold rolled (Temper H18) and recrystallised (Temper O) to examine the effect of these treatments on the tensile mechanical properties. During cold rolling (Temper H-18), grain alignment occurred with a yield stress, maximum stress, and elongation of 209.5 MPa, 210.1 MPa, and 2.8%, respectively. The strength decreased (yield stress of 58 MPa and maximum stress of 120.2 MPa) under recrystallisation conditions (Temper O), but the ductility increased (8.9%). This is in contrast to the Al-Si (Al 10Si) strip, which exhibited a yield stress, maximum stress, and elongation of 103.3 MPa, 128.7 MPa, and 1.9%, respectively. The A1 10Si strips also fractured during cold rolling, indicating high material fragility.

EnsMulHateCyb: Multilingual hate speech and cyberbully detection in online social media

Nowadays, users across the globe interact with one another for information exchange, communication, and association on various online social media. However, some individuals exploit these venues for malicious practices like hate speech and cyberbully. In this paper, we present an improved multilingual hate speech and cyberbully detection model using bagging-stacking based hybrid ensemble deep learning techniques. The proposed model utilizes Bi-directional Long Short-Term Memory (BiLSTM), Bi-directional Gated Recurrent Unit (Bi-GRU), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) techniques to enhance the overall performance. We first preprocess the multilingual data streams followed by adoption of Global vectors for word Representation (GloVe) embeddings to convert words to a vector representation in parallel enabling the data streams for binary classification task. In order to construct an architecture for the detection of hate speech and cyberbully, we introduce a heterogeneous fusion of multiple effective models in a unique approach such that CNN-LSTM utilizes a stacking approach with stochastic gradient descent to achieve optimal weights, whereas all the base learners used bagging ensemble approach with cross-validation to reach optimal weights. The final output layer of the proposed ensemble deep learning architecture is achieved using a super learner approach on base learners. To show the efficacy of the proposed model, we conduct the simulation on a total of nine real-world social media datasets in different languages and compared the results with other contemporary hate speech and cyberbully detection methods. The collected findings show that the proposed model outperforms other models on considered datasets and shows an improvement of at least 4.44% in F1 scores.