To address the challenge of sealant debonding due to cyclic temperature variations, a new pavement crack repair sealant which can achieve two-way shape memory deformation is developed. The developed ...crack sealant is a shape memory liquid crystal elastomer (SMLCE), designed to exhibit the deformation characteristics of heat contraction and cold expansion. First, the material composition and preparation process of the developed SMLCE are given. Thermodynamic properties, phase transition temperatures and molecular structures are analyzed based on DSC and FITR. The effects of the crosslinker and chain extender ratios and the key preparation processes on the two-way shape memory deformation and mechanical performance of SMLCE are systematically analyzed. Based on the analysis, the optimum ratio of SMLCE is determined to be 1:15 and the optimum secondary crosslinking preparation process is 150% orientation stretching. Under the optimal solution, the developed SMLCE can achieve the multiple two-way shape memory reversible deformation with a maximum 46% deformation in the temperature range of -20°C∼120°C. At the same time, the developed SMLCE has excellent mechanical properties, with a tensile strength of 20.7Mpa and an elongation at break of 322%. It also exhibits good low-temperature deformation capabilities at -10°C and above. Finally, the suitability and application potential of the developed two-way SMLCE as a pavement crack sealant are assessed. The developed SMLCE has good adaptability in most climate zones, which indicates its great potential as a pavement crack sealant. This research provides a new way for the pavement crack repair.
•The developed SMLCE sealant with a two-way shape memory deformation effect.•Multiple two-way shape memory reversible deformation ability in the range of -20°C∼120°C.•Under the optimal solution, the maximum shape memory shrinkage rate reaches 47%, the tensile strength reaches 20.7 MPa, and the elongation at break reaches 322%.
•First investigation on a complete sentiment quadruple extraction task for Chinese product reviews.•Development of a two-stage neural model composed of multiple efficient network modules.•Multi-task ...learning for three sequence labeling subtasks in the first stage.•Synchronous learning for the proposed models in the first stage and the second stage.
Aspect-based sentiment analysis (ABSA) is a fine-grained task which aims to identify the emotional polarity of a specific aspect in a text or sentence. Aspect term extraction (ATE), opinion term extraction (OTE) and aspect polarity classification (APC) are three main subtasks of the ABSA task. Nowadays, researchers mainly focus on a single task or a joint task composed of these three subtasks, and such investigation on the sentiment analysis is not sufficient. In this paper, we firstly introduce a complete aspect sentiment analysis task, called Aspect Sentiment Quadruple Extraction, which also includes the category detection beside ATE, OTE and APC. Then we propose a two-stage neural network model composed of several modules, including BiLSTM, simple gated self-attention and position encoding for this joint task. In the first stage, the proposed model extracts aspect and opinion terms as well as their categories and polarities. Moreover, the second stage mainly includes a relation classifier to validate the aspect-opinion pairs and then finalizes the complete quadruple extraction. The experimental results, evaluated on a benchmark dataset of Chinese product reviews, show that our proposed model outperforms other baseline methods and achieves the start-of-art performance.
Oxygen free radical damage is regarded as a direct or indirect common pathway associated with diabetic neuropathy and is the main cause of complications in peripheral neuropathies. We speculate that ...Jiaweibugan decoction has a significant effect in treating diabetic peripheral neuropathy through an anti-oxidative stress pathway. In this study, a diabetic rat model was established by intraperitoneal injection of streptozotocin. Rats were treated with Jiaweibugan decoction via intragastric administration. The levels of malondialdehyde and glutathione, which are indirect indexes of oxidative stress, in serum were determined using a colorimetric method. The expression levels of nuclear factor kappa B p65 mRNA and p38 mitogen-activated protein kinase, which are oxidative stress associated factors, in the dorsal root ganglion of spinal S4-6 segments were evaluated by reverse-transcriptase polymerase chain reaction and immunohistochemistry. Results showed that, Jiaweibugan decoction significantly ameliorated motor nerve conduction velocity in diabetic rats, effectively decreased malondialdehyde levels in serum and the expression of nuclear factor kappa B p65 mRNA and p38 mitogen-activated protein kinase mRNA in the dorsal root ganglion, and increased glutathione levels in serum. Therefore, our experimental findings indicate that Jiaweibugan decoction plays an anti-oxidative stress role in the diabetic peripheral neuropathy process, which has a protective effect on peripheral nerve injury.
This paper evaluates the influences of variations in asphalt mixture parameters during construction on the variations of pavement performance using back-propagation (BP) neural networks. The ...variations of gradation (VG) and asphalt-aggregate ratio (VRa) were assessed through a variability analysis. The influences of VG and VRa propagation were analyzed via BP neural networks and a sensitivity analysis. A reliability assessment was conducted to evaluate the joint effects of VG and VRa. Results illustrate that the VG and VRa during transportation are more severe than those during other processes. BP neural networks can precisely and robustly trace the influences of the VG and VRa. Pavement performance exhibits greater sensitivity to VRa and VG at sieve sizes of 0.075 mm and 2.36 mm. The joint effects of VG and VRa significantly degrade permanent deformation more than fatigue life. High-quality paving effectively mitigates the negative impacts of segregation during transportation.
Display omitted
•Variations of gradation (VG) and asphalt-aggregate ratio (VRa) are more severe during transportation.•BP neural networks effectively trace the fluences of VG and VRa on pavement performance.•The joint effects of VG and VRa degrade permanent deformation more than fatigue life.•High-quality paving mitigates segregation impacts during transportation.
Under the background of the Internet of Energy (IoE), building the distributed energy resources management system (DERMS) is the premise for further research on a virtual power plant (VPP). Now, the ...design solutions of DERMS are mostly based on supervisory control and data acquisition (SCADA) architecture and mainstream Industrial Internet of Things (IIoT) architecture. Both have the problems of obvious centralization characteristics and complex system layers. Hence, we propose a decentralized IPT cloud/fog architecture. IPT fog connects with underlying devices through fog nodes. IPT cloud connects multiple IPT fogs and provides local and remote services. Compared with the existing solutions, this architecture can achieve the same time synchronization accuracy and has better performance in terms of system layers, real-time capacity, construction speed, and availability. The synchronization accuracy is less than 1 <inline-formula> <tex-math notation="LaTeX">\mu \text{s} </tex-math></inline-formula>. The I/O response time within the fog network is less than 1 ms, and that across the fog network is less than 10 ms. Finally, a specific application case of a wastewater treatment VPP is introduced to verify the feasibility of the IPT cloud/fog architecture.
Display omitted
•Multiple aggregate shape classification methods were compared and analyzed.•Multi-view features were constructed by combining multiple single-view features.•Multi-view images were ...constructed by fusing morphologies from different views.•SVM and Resnet18 were adopted for aggregate shape classification.•Both multi-view features and multi-view images have significant 3D shape characterization ability.
The content of elongated and flat aggregates is a critical detection index in road engineering. In this study, using image sequences of falling aggregates, two multi-view morphological methods were proposed for aggregate shape classification. The multi-view features of the aggregates were constructed by combining multiple single-view features from different views. Furthermore, a joint-view normalization method was proposed to improve the three-dimensional shape characterization capability of the multi-view features. Based on the multi-view features, a support vector machine was adopted to achieve aggregate shape classification. In addition, multiple two-dimensional aggregate morphologies from different views were directionally guided and fused to construct a multi-view image, which could reflect the three-dimensional shape of the aggregates. The multi-view images were then fed into ResNet18 for aggregate-shape classification. Notably, compared with single-view morphological methods based on the aggregate morphology in the vertical and random views, the two multi-view morphological methods developed herein significantly improved the classification accuracy. Moreover, it was found experimentally that increasing the height of the field of view improved the classification accuracy of the multi-view morphological methods. The proposed multi-view morphological methods demonstrate significant potential for application in the automatic identification of elongated and flat aggregates in road construction.
A complete sentiment analysis of product and service reviews has attracted growing concerns from merchants to enhance personalized marketing activities. Aspect sentiment quadruple prediction (ASQP) ...is a demanding and challenging task with the objective to predict four sentiment elements from given reviews. Existing methods for ASQP face certain issues, with pipeline-based non-generative approaches prone to error propagation and generative models at the potential risk of producing unexpected outputs or longer inference times. To avoid these shortcomings, we develop a novel end-to-end non-generative model for ASQP involving multi-task decomposition within machine reading comprehension (MRC) framework. Specifically, the ASQP task is decomposed into six query-induced subtasks by introducing task-specific question templates. The proposed model, named MRC-CLRI, is trained with multi-task joint learning. It also incorporates contrastive learning for category identification and sentiment classification to enhance the correlation of the six subtasks. To further promote the quadruple prediction, we present a refined inference algorithm in a bidirectional multi-turn inference procedure to effectively match aspect and opinion terms and optimize two inference hyperparameters: distance threshold and probability threshold. Experimental results exhibit superior performance compared to existing two non-generative and seven generative baselines. Our proposed MRC-CLRI, as a novel non-generative model, outperforms the best existing generative method by an average F1 score improvement of 1.69% and the best previous non-generative method by an average F1 score improvement of 15.77% across four review datasets. Ablation experiments further validate the efficacy of the designed contrastive learning and the refined inference algorithm.
•The ASQP task is firstly addressed through decomposing it into six query-induced subtasks within MRC framework.•Contrastive learning for category and sentiment classifications is incorporated to enhance the multi-task joint learning.•A refined inference algorithm is presented to enhance the sentiment quadruple prediction.•The proposed end-to-end non-generative MRC-CLRI surpasses the current top-performing generative method.
Display omitted
•A single industrial camera was used to obtain the morphologies of aggregate particles in multiple views.•A general regression neural network was adopted for classification of ...aggregate particles.•Different equivalent geometric models for aggregate result in different multi-view shape features.•The accuracy of aggregate particle classification can be improved by increasing the frame rate.
Aggregate is an important component of asphalt mixtures, and its shape has a significant influence on the road quality. In this study, a single industrial camera was used to collect images of aggregate particles during falling; then, their morphologies obtained in multiple views were analyzed. Using the equivalent geometric model, four shape characterization parameters—area variety factor, minor diameter variety factor, maximum elongation factor, and Strip-Block area variety factor—were proposed to compose the multi-view shape feature. On this basis, a general regression neural network was adopted to realize the classification of aggregate particles. The results show that the aggregate classification is slightly different when using different equivalent geometric models, while the aggregate shape can be effectively classified. The accuracy of aggregate classification can be improved by fusing parameters from different equivalent models using principal component analysis; another way is through increasing the frame rate of image collection that may increase the number of views. In general, the findings indicate that the proposed detection method can be applied to actual road engineering, which is of great significance to guarantee pavement quality.
Yarn supercapacitors (YSCs) are attracting considerable interest for wearable electronics and intelligent textiles due to their high flexibility and weavability. In the present study, stainless ...steel/cotton blended yarns were used as supports and current collectors to produce polypyrrole-coated yarn electrodes. The as-made YSC exhibited a high areal specific capacitance of 344 mF cm
−2
at a current density of 0.6 mA cm
−2
and good cycling stability (almost 93% capacitance retention over 1000 cycles). Moreover, the YSC could be knitted into other fabrics without damaging its original structure and electrochemical performance owing to its superior flexibility, indicating that it can meet the requirements of energy-storage devices for wearable electronics.
Graphical abstract
The interaction between DNA and protein is vital for the development of a living body. Previous numerous studies on in silico identification of DNA-binding proteins (DBPs) usually include features ...extracted from the alignment-based (pseudo) position-specific scoring matrix (PSSM), leading to limited application due to its time-consuming generation. Few researchers have paid attention to the application of pretrained language models at the scale of evolution to the identification of DBPs. To this end, we present comprehensive insights into a comparison study on alignment-based PSSM and pretrained evolutionary scale modeling (ESM) representations in the field of DBP classification. The comparison is conducted by extracting information from PSSM and ESM representations using four unified averaging operations and by performing various feature selection (FS) methods. Experimental results demonstrate that the pretrained ESM representation outperforms the PSSM-derived features in a fair comparison perspective. The pretrained feature presentation deserves wide application to the area of in silico DBP identification as well as other function annotation issues. Finally, it is also confirmed that an ensemble scheme by aggregating various trained FS models can significantly improve the classification performance of DBPs.