Synthesis and application of waste-based layered double hydroxide: A review.

The synthesis of layered double hydroxide (LDH) from industrial wastes is a sustainable approach to aid circular economy and hazardous material disposal. In this review, the researches on the synthesis and application of waste-based LDH from 2010 to 2023 are summarized and discussed. At present, there are mainly four types of waste-based LDH produced from red mud, slag, fly ash and wastewater, with co-precipitation being the most typical synthesis method. Red mud is used as the trivalent metal source supplemented by chemical reagents or other types of waste as divalent metal source to produce red mud-based LDH. Slag can act as the sole metal source providing both divalent and trivalent metal sources for slag-based LDH. Fly ash was used either as the trivalent metal source or both divalent and trivalent metal sources to produce fly ash-based LDH. Wastewater-based LDH was typically synthesized by in-situ co-precipitation method to achieve the self-purification of wastewater. The impurities in waste-based LDH can act as a two-edged weapon. It may either hinder or promote the performance of waste-based LDH. The challenge in the synthesis of waste-based LDH lies in the efficient extraction of available metals. The future research prospects for waste-based LDH are suggested.

Biochar implications for the engineering properties of soils: A review.

Use of biochar as a soil amendment for climate change mitigation and environmental remediation has been intensively studied over the past decade, yet the growing interest in biochar for geo-environmental applications is primarily motivated by its active interactions with soil in terms of engineering properties. The addition of biochar can significantly alter the physical, hydrological, and mechanical properties of soils, but the diverse biochar characteristics and soil properties lead to the fact that a generalized conclusion on the impact of biochar on soil engineering properties is difficult to reach. Considering that the effects of biochar on soil engineering properties could also potentially affect the applications of biochar in other fields, this review intends to provide a comprehensive and critical overview of biochar implications for soil engineering properties. Based on the physicochemical properties of biochar pyrolyzed from varying feedstocks and pyrolysis temperatures, this review analyzed the physical, hydrological, and mechanical performances of biochar-amended soils and the underlying mechanisms. Among others, the analysis releases that the initial state of biochar-amended soil requires special attention when evaluating the effect of biochar on soil engineering properties, yet it is usually neglected in the current studies. The review closes with a brief overview of the potential impacts of engineering properties on other soil processes, and future needs and opportunities for further development of biochar in geo-environmental engineering from academia to practice.

Microbial­induced carbonate precipitation (MICP) technology: a review on the fundamentals and engineering applications.

The microbial­induced carbonate precipitation (MICP), as an emerging biomineralization technology mediated by specific bacteria, has been a popular research focus for scientists and engineers through the previous two decades as an interdisciplinary approach. It provides cutting-edge solutions for various engineering problems emerging in the context of frequent and intense human activities. This paper is aimed at reviewing the fundaments and engineering applications of the MICP technology through existing studies, covering realistic need in geotechnical engineering, construction materials, hydraulic engineering, geological engineering, and environmental engineering. It adds a new perspective on the feasibility and difficulty for field practice. Analysis and discussion within different parts are generally carried out based on specific considerations in each field. MICP may bring comprehensive improvement of static and dynamic characteristics of geomaterials, thus enhancing their bearing capacity and resisting liquefication. It helps produce eco-friendly and durable building materials. MICP is a promising and cost-efficient technology in preserving water resources and subsurface fluid leakage. Piping, internal erosion and surface erosion could also be addressed by this technology. MICP has been proved suitable for stabilizing soils and shows promise in dealing with problematic soils like bentonite and expansive soils. It is also envisaged that this technology may be used to mitigate against impacts of geological hazards such as liquefaction associated with earthquakes. Moreover, global environment issues including fugitive dust, contaminated soil and climate change problems are assumed to be palliated or even removed via the positive effects of this technology. Bioaugmentation, biostimulation, and enzymatic approach are three feasible paths for MICP. Decision makers should choose a compatible, efficient and economical way among them and develop an on-site solution based on engineering conditions. To further decrease the cost and energy consumption of the MICP technology, it is reasonable to make full use of industrial by-products or wastes and non-sterilized media. The prospective direction of this technology is to make construction more intelligent without human intervention, such as autogenous healing. To reach this destination, MICP could be coupled with other techniques like encapsulation and ductile fibers. MICP is undoubtfully a mainstream engineering technology for the future, while ecological balance, environmental impact and industrial applicability should still be cautiously treated in its real practice.

GAM-SpCaNet: Gradient awareness minimization-based spinal convolution attention network for brain tumor classification.

Brain tumor is one of the common diseases of the central nervous system, with high morbidity and mortality. Due to the wide range of brain tumor types and pathological types, the same type is divided into different subgrades. The imaging manifestations are complex, making clinical diagnosis and treatment difficult. In this paper, we construct SpCaNet (Spinal Convolution Attention Network) to effectively utilize the pathological features of brain tumors, consisting of a Positional Attention (PA) convolution block, Relative self-attention transformer block, and Intermittent fully connected (IFC) layer. Our method is more lightweight and efficient in recognition of brain tumors. Compared with the SOTA model, the number of parameters is reduced by more than three times. In addition, we propose the gradient awareness minimization (GAM) algorithm to solve the problem of insufficient generalization ability of the traditional Stochastic Gradient Descent (SGD) method and use it to train the SpCaNet model. Compared with SGD, GAM achieves better classification performance. According to the experimental results, our method has achieved the highest accuracy of 99.28%, and the proposed method performs well in classifying brain tumors.

CTMLP: Can MLPs replace CNNs or transformers for COVID-19 diagnosis?

BACKGROUND: Convolutional Neural Networks (CNNs) and the hybrid models of CNNs and Vision Transformers (VITs) are the recent mainstream methods for COVID-19 medical image diagnosis. However, pure CNNs lack global modeling ability, and the hybrid models of CNNs and VITs have problems such as large parameters and computational complexity. These models are difficult to be used effectively for medical diagnosis in just-in-time applications. METHODS: Therefore, a lightweight medical diagnosis network CTMLP based on convolutions and multi-layer perceptrons (MLPs) is proposed for the diagnosis of COVID-19. The previous self-supervised algorithms are based on CNNs and VITs, and the effectiveness of such algorithms for MLPs is not yet known. At the same time, due to the lack of ImageNet-scale datasets in the medical image domain for model pre-training. So, a pre-training scheme TL-DeCo based on transfer learning and self-supervised learning was constructed. In addition, TL-DeCo is too tedious and resource-consuming to build a new model each time. Therefore, a guided self-supervised pre-training scheme was constructed for the new lightweight model pre-training. RESULTS: The proposed CTMLP achieves an accuracy of 97.51%, an f1-score of 97.43%, and a recall of 98.91% without pre-training, even with only 48% of the number of ResNet50 parameters. Furthermore, the proposed guided self-supervised learning scheme can improve the baseline of simple self-supervised learning by 1%-1.27%. CONCLUSION: The final results show that the proposed CTMLP can replace CNNs or Transformers for a more efficient diagnosis of COVID-19. In addition, the additional pre-training framework was developed to make it more promising in clinical practice.

Enhancing lead immobilization by biochar: Creation of "surface barrier" via bio-treatment.

The long-term effectiveness of heavy metal immobilization is always a concern. This study proposes a completely novel approach to enhance the stability of heavy metals by combined biochar and microbial induced carbonate precipitation (MICP) technology, to create a "surface barrier" of CaCO3 layer on biochar after lead (Pb2+) immobilization. Aqueous sorption studies and chemical and micro-structure tests were used to verify the feasibility. Rice straw biochar (RSB700) was produced at 700 °C, which shows high immobilization capacity of Pb2+ (maximum of 118 mg g-1). But the stable fraction only accounts for 4.8% of the total immobilized Pb2+ on biochar. After MICP treatment, the stable fraction of Pb2+ significantly increased to a maximum of 92.5%. Microstructural tests confirm the formation of CaCO3 layer on biochar. The CaCO3 species are predominantly calcite and vaterite. Higher Ca2+ and urea concentrations in cementation solution resulted in higher CaCO3 yield but lower Ca2+ utilization efficiency. The main mechanism of the "surface barrier" to enhance Pb2+ stability on biochar was likely the encapsulation effect: it physically blocked the contact between acids and Pb2+ on biochar, and chemically buffer the acidic attack from the environment. The performance of the "surface barrier" depends on both the yield of CaCO3 and their distribution uniformity on biochar's surface. This study shed lights on the potential application of the "surface barrier" strategy combining biochar and MICP technologies for enhanced heavy metal immobilization.

DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network.

To address the problems of under-segmentation and over-segmentation of small organs in medical image segmentation. We present a novel medical image segmentation network model with Depth Separable Gating Transformer and a Three-branch Attention module (DSGA-Net). Firstly, the model adds a Depth Separable Gated Visual Transformer (DSG-ViT) module into its Encoder to enhance (i) the contextual links among global, local, and channels and (ii) the sensitivity to location information. Secondly, a Mixed Three-branch Attention (MTA) module is proposed to increase the number of features in the up-sampling process. Meanwhile, the loss of feature information is reduced when restoring the feature image to the original image size. By validating Synapse, BraTs2020, and ACDC public datasets, the Dice Similarity Coefficient (DSC) of the results of DSGA-Net reached 81.24%,85.82%, and 91.34%, respectively. Moreover, the Hausdorff Score (HD) decreased to 20.91% and 5.27% on the Synapse and BraTs2020. There are 10.78% and 0.69% decreases compared to the Baseline TransUNet. The experimental results indicate that DSGA-Net achieves better segmentation than most advanced methods.

CsAGP: Detecting Alzheimer's disease from multimodal images via dual-transformer with cross-attention and graph pooling.

Alzheimer's disease (AD) is a terrible and degenerative disease commonly occurring in the elderly. Early detection can prevent patients from further damage, which is crucial in treating AD. Over the past few decades, it has been demonstrated that neuroimaging can be a critical diagnostic tool for AD, and the feature fusion of different neuroimaging modalities can enhance diagnostic performance. Most previous studies in multimodal feature fusion have only concatenated the high-level features extracted by neural networks from various neuroimaging images simply. However, a major problem of these studies is over-looking the low-level feature interactions between modalities in the feature extraction stage, resulting in suboptimal performance in AD diagnosis. In this paper, we develop a dual-branch vision transformer with cross-attention and graph pooling, namely CsAGP, which enables multi-level feature interactions between the inputs to learn a shared feature representation. Specifically, we first construct a brand-new cross-attention fusion module (CAFM), which processes MRI and PET images by two independent branches of differing computational complexity. These features are fused merely by the cross-attention mechanism to enhance each other. After that, a concise graph pooling algorithm-based Reshape-Pooling-Reshape (RPR) framework is developed for token selection to reduce token redundancy in the proposed model. Extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrated that the suggested method obtains 99.04%, 97.43%, 98.57%, and 98.72% accuracy for the classification of AD vs. CN, AD vs. MCI, CN vs. MCI, and AD vs. CN vs. MCI, respectively.

NSCGCN: A novel deep GCN model to diagnosis COVID-19.

AIM: Corona Virus Disease 2019 (COVID-19) was a lung disease with high mortality and was highly contagious. Early diagnosis of COVID-19 and distinguishing it from pneumonia was beneficial for subsequent treatment. OBJECTIVES: Recently, Graph Convolutional Network (GCN) has driven a significant contribution to disease diagnosis. However, limited by the nature of the graph convolution algorithm, deep GCN has an over-smoothing problem. Most of the current GCN models are shallow neural networks, which do not exceed five layers. Furthermore, the objective of this study is to develop a novel deep GCN model based on the DenseGCN and the pre-trained model of deep Convolutional Neural Network (CNN) to complete the diagnosis of chest X-ray (CXR) images. METHODS: We apply the pre-trained model of deep CNN to perform feature extraction on the data to complete the extraction of pixel-level features in the image. And then, to extract the potential relationship between the obtained features, we propose Neighbourhood Feature Reconstruction Algorithm to reconstruct them into graph-structured data. Finally, we design a deep GCN model that exploits the graph-structured data to diagnose COVID-19 effectively. In the deep GCN model, we propose a Node-Self Convolution Algorithm (NSC) based on feature fusion to construct a deep GCN model called NSCGCN (Node-Self Convolution Graph Convolutional Network). RESULTS: Experiments were carried out on the Computed Tomography (CT) and CXR datasets. The results on the CT dataset confirmed that: compared with the six state-of-the-art (SOTA) shallow GCN models, the accuracy and sensitivity of the proposed NSCGCN had improve 8% as sensitivity (Sen.) = 87.50%, F1 score = 97.37%, precision (Pre.) = 89.10%, accuracy (Acc.) = 97.50%, area under the ROC curve (AUC) = 97.09%. Moreover, the results on the CXR dataset confirmed that: compared with the fourteen SOTA GCN models, sixteen SOTA CNN transfer learning models and eight SOTA COVID-19 diagnosis methods on the COVID-19 dataset. Our proposed method had best performances as Sen. = 96.45%, F1 score = 96.45%, Pre. = 96.61%, Acc. = 96.45%, AUC = 99.22%. CONCLUSION: Our proposed NSCGCN model is effective and performed better than the thirty-eight SOTA methods. Thus, the proposed NSC could help build deep GCN models. Our proposed COVID-19 diagnosis method based on the NSCGCN model could help radiologists detect pneumonia from CXR images and distinguish COVID-19 from Ordinary Pneumonia (OPN). The source code of this work will be publicly available at https://github.com/TangChaosheng/NSCGCN.

Effects of biochar particle size and dosage on the desiccation cracking behavior of a silty clay.

Desiccation cracking can significantly change the integrity of soils, and potentially result in the instability of infrastructure as well as the migration of contaminants. Biochar is regarded as a promising low-carbon material for geotechnical applications, including cracking prevention. This study investigates the effects of biochar particle size and dosage on the desiccation cracking characteristics of a silty clay. For samples with fine biochar particles (<0.25 mm), coarser primary cracks initiate first, followed by finer secondary cracks regardless of biochar dosage. Quantitative analysis of the cracking characteristics at the stable stage shows that the surface crack ratio, the number of crack segments, the total length of cracks and the average width of cracks decreased by 31.29%, 30.78%, 14.18%, and 20.45% after 10% biochar addition. For samples with coarse biochar particles (>0.25 mm), cracks initiate simultaneously on the soil surface, and primary and secondary cracks are difficult to distinguish after drying, especially in high dosage samples. In the presence of 10% biochar, the surface crack ratio and average width of cracks decreased by 28.64% and 62.84%, but the number of crack segments and total length of cracks increased by 163.39% and 42.13%. Microstructure and image processing analysis of soil cracks indicate that biochar affects the crack initiation and propagation process by altering the soil microstructure and thereby the crack parameters. The contact between biochar and soil particles transitions from close contact to loose contact as the size of the biochar particles increases. In general, the application of 10% biochar with fine particle size had the best performance in inhibiting soil cracking.

TSRNet: Diagnosis of COVID-19 based on self-supervised learning and hybrid ensemble model.

BACKGROUND: As of Feb 27, 2022, coronavirus (COVID-19) has caused 434,888,591 infections and 5,958,849 deaths worldwide, dealing a severe blow to the economies and cultures of most countries around the world. As the virus has mutated, its infectious capacity has further increased. Effective diagnosis of suspected cases is an important tool to stop the spread of the pandemic. Therefore, we intended to develop a computer-aided diagnosis system for the diagnosis of suspected cases. METHODS: To address the shortcomings of commonly used pre-training methods and exploit the information in unlabeled images, we proposed a new pre-training method based on transfer learning with self-supervised learning (TS). After that, a new convolutional neural network based on attention mechanism and deep residual network (RANet) was proposed to extract features. Based on this, a hybrid ensemble model (TSRNet) was proposed for classifying lung CT images of suspected patients as COVID-19 and normal. RESULTS: Compared with the existing five models in terms of accuracy (DarkCOVIDNet: 98.08%; Deep-COVID: 97.58%; NAGNN: 97.86%; COVID-ResNet: 97.78%; Patch-based CNN: 88.90%), TSRNet has the highest accuracy of 99.80%. In addition, the recall, f1-score, and AUC of the model reached 99.59%, 99.78%, and 1, respectively. CONCLUSION: TSRNet can effectively diagnose suspected COVID-19 cases with the help of the information in unlabeled and labeled images, thus helping physicians to adopt early treatment plans for confirmed cases.

MFBCNNC: Momentum factor biogeography convolutional neural network for COVID-19 detection via chest X-ray images.

AIM: By October 6, 2020, Coronavirus disease 2019 (COVID-19) was diagnosed worldwide, reaching 3,355,7427 people and 1,037,862 deaths. Detection of COVID-19 and pneumonia by the chest X-ray images is of great significance to control the development of the epidemic situation. The current COVID-19 and pneumonia detection system may suffer from two shortcomings: the selection of hyperparameters in the models is not appropriate, and the generalization ability of the model is poor. METHOD: To solve the above problems, our team proposed an improved intelligent global optimization algorithm, which is based on the biogeography-based optimization to automatically optimize the hyperparameters value of the models according to different detection objectives. In the optimization progress, after selecting the immigration of suitable index vector and the emigration of suitable index vector, we proposed adding a comparison operation to compare the value of them. According to the different numerical relationships between them, the corresponding operations are performed to improve the migration operation of biogeography-based optimization. The improved algorithm (momentum factor biogeography-based optimization) can better perform the automatic optimization operation. In addition, our team also proposed two frameworks: biogeography convolutional neural network and momentum factor biogeography convolutional neural network. And two methods for detection COVID-19 based on the proposed frameworks. RESULTS: Our method used three convolutional neural networks (LeNet-5, VGG-16, and ResNet-18) as the basic classification models for chest X-ray images detection of COVID-19, Normal, and Pneumonia. The accuracy of LeNet-5, VGG-16, and ResNet-18 is improved by 1.56%, 1.48%, and 0.73% after using biogeography-based optimization to optimize the hyperparameters of the models. The accuracy of LeNet-5, VGG-16, and ResNet-18 is improved by 2.87%, 6.31%, and 1.46% after using the momentum factor biogeography-based optimization to optimize the hyperparameters of the models. CONCLUSION: Under the same experimental conditions, the performance of the momentum factor biogeography-based optimization is superior to the biogeography-based optimization in optimizing the hyperparameters of the convolutional neural networks. Experimental results show that the momentum factor biogeography-based optimization can improve the detection performance of the state-of-the-art approaches in terms of overall accuracy. In future research, we will continue to use and improve other global optimization algorithms to enhance the application ability of deep learning in medical pathological image detection.

Impact of biochar on the desiccation cracking behavior of silty clay and its mechanisms.

Biochar has recently been widely used in environmental geotechnical engineering. However, its impact on soil cracking is not fully understood. In this study, the influence of different wood biochar dosages on the desiccation cracking characteristics of silty clay was studied, and the mechanism was elucidated through a combination of image and microstructural analysis. The results indicate biochar affects the desiccation cracking characteristics of soil across the whole process of water evaporation and crack development. The evaporation rate decreased with low amounts of biochar, but increased as the biochar content increased. At the stage of crack development, the addition of biochar increased the soil cracking water content, induced the formation of annular cracks in soil, and changed the soil crack development process. Quantitative results of the stabilized cracks show the surface crack ratio was decreased by 11.59% and 34.32%, and the average crack width was decreased by 14.83%, and 34.51%, after 5% and 10% biochar addition, respectively. Meanwhile, most of the single cracks in biochar-amended soil are fine. In addition, the surface crack ratio of soil without biochar addition first increased and then stabilized with an increase in the number of wetting-drying (W-D) cycles, while that of the biochar-amended soil decreased slightly. Comparing the crack networks after one and five W-D cycles, the number of cracks formed with 5% and 10% biochar addition decreased by -1.51% and 19.24%, and 15.29%, and 36.92%, respectively, indicating that after the addition of biochar, the soil becomes more resistant to cracking under W-D cycles. In summary, the addition of biochar may have inhibited desiccation cracking by (1) reducing the tensile stress on the soil surface, (2) increasing the repulsive forces between soil particles, (3) occupying the shrinkage space between soil particles, and (4) reducing the tensile strength between soil particles.

Cerebral Micro-Bleeding Detection Based on Densely Connected Neural Network.

Cerebral micro-bleedings (CMBs) are small chronic brain hemorrhages that have many side effects. For example, CMBs can result in long-term disability, neurologic dysfunction, cognitive impairment and side effects from other medications and treatment. Therefore, it is important and essential to detect CMBs timely and in an early stage for prompt treatment. In this research, because of the limited labeled samples, it is hard to train a classifier to achieve high accuracy. Therefore, we proposed employing Densely connected neural network (DenseNet) as the basic algorithm for transfer learning to detect CMBs. To generate the subsamples for training and test, we used a sliding window to cover the whole original images from left to right and from top to bottom. Based on the central pixel of the subsamples, we could decide the target value. Considering the data imbalance, the cost matrix was also employed. Then, based on the new model, we tested the classification accuracy, and it achieved 97.71%, which provided better performance than the state of art methods.

Alcoholism Identification Based on an AlexNet Transfer Learning Model.

Aim: This paper proposes a novel alcoholism identification approach that can assist radiologists in patient diagnosis. Method: AlexNet was used as the basic transfer learning model. The global learning rate was small, at 10-4, and the iteration epoch number was at 10. The learning rate factor of replaced layers was 10 times larger than that of the transferred layers. We tested five different replacement configurations of transfer learning. Results: The experiment shows that the best performance was achieved by replacing the final fully connected layer. Our method yielded a sensitivity of 97.44%± 1.15%, a specificity of 97.41 ± 1.51%, a precision of 97.34 ± 1.49%, an accuracy of 97.42 ± 0.95%, and an F1 score of 97.37 ± 0.97% on the test set. Conclusion: This method can assist radiologists in their routine alcoholism screening of brain magnetic resonance images.

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling.

Aim: Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important. Method: This study proposed a 14-layer convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run. Results: The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%. Conclusion: Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.

Satellite-derived subsurface urban heat island.

The subsurface urban heat island (SubUHI) is one part of the overall UHI specifying the relative warmth of urban ground temperatures against the rural background. To combat the challenge on measuring extensive underground temperatures with in situ instruments, we utilized satellite-based moderate-resolution imaging spectroradiometer data to reconstruct the subsurface thermal field over the Beijing metropolis through a three-time-scale model. The results show the SubUHI's high spatial heterogeneity. Within the depths shallower than 0.5 m, the SubUHI dominates along the depth profiles and analyses imply the moments for the SubUHI intensity reaching first and second extremes during a diurnal temperature cycle are delayed about 3.25 and 1.97 h per 0.1 m, respectively. At depths shallower than 0.05 m in particular, there is a subsurface urban cool island (UCI) in spring daytime, mainly owing to the surface UCI that occurs in this period. At depths between 0.5 and 10 m, the time for the SubUHI intensity getting to its extremes during an annual temperature cycle is lagged 26.2 days per meter. Within these depths, the SubUHI prevails without exception, with an average intensity of 4.3 K, varying from 3.2 to 5.3 K.