Underwater vital signs monitoring of respiratory rate, blood pressure, and the heart's status is essential for healthcare and sports management. Real‐time electrocardiography (ECG) monitoring ...underwater can be one solution for this. However, the current electrodes used for ECGs are not suitable for aquatic applications since they may lose their adhesiveness to skin, stable conductivity, or/and structural stability when immersed into water. Here, the design and fabrication of water‐resistant electrodes to repurpose stretchable electrodes for applications in an aquatic environment are reported. The electrodes are composed of stretchable metal–polymer composite film as the substrate and dopamine‐containing polymer as a coating. The polymer is designed to possess underwater adhesiveness from the dopamine motif, water stability from the main scaffold, and ionic conductivity from the carboxyl groups for signal transmission. Stable underwater conductivity and firm adhesion to skin allow the electrodes to collect reliable ECG signals under various conditions in water. It is shown that wearable devices incorporated with the water‐resistant electrodes can acquire real‐time ECG signals during swimming, which can be used for revealing the heart condition. These water‐resistant electrodes realize underwater detection of ECG signals and can be used for health monitoring and sports management during aquatic activities.
Water‐resistant stretchable electrodes are fabricated with a specially designed polymer. The polymer is adhesive underwater to bridge the electrode and skin, and ionic‐conductive to transmit electrophysiological signals. The conformal electrodes realize reliable electrocardiography (ECG) detection when moving the body or being impacted with water flow, which enables stable wireless real‐time ECG collection during swimming with a wearable device.
A review of Earth Artificial Intelligence Sun, Ziheng; Sandoval, Laura; Crystal-Ornelas, Robert ...
Computers & geosciences,
February 2022, 2022-02-00, 2022-02-01, Letnik:
159, Številka:
C
Journal Article
Recenzirano
Odprti dostop
In recent years, Earth system sciences are urgently calling for innovation on improving accuracy, enhancing model intelligence level, scaling up operation, and reducing costs in many subdomains amid ...the exponentially accumulated datasets and the promising artificial intelligence (AI) revolution in computer science. This paper presents work led by the NASA Earth Science Data Systems Working Groups and ESIP machine learning cluster to give a comprehensive overview of AI in Earth sciences. It holistically introduces the current status, technology, use cases, challenges, and opportunities, and provides all the levels of AI practitioners in geosciences with an overall big picture and to “blow away the fog to get a clearer vision” about the future development of Earth AI. The paper covers all the majorspheres in the Earth system and investigates representative AI research in each domain. Widely used AI algorithms and computing cyberinfrastructure are briefly introduced. The mandatory steps in a typical workflow of specializing AI to solve Earth scientific problems are decomposed and analyzed. Eventually, it concludes with the grand challenges and reveals the opportunities to give some guidance and pre-warnings on allocating resources wisely to achieve the ambitious Earth AI goals in the future.
•A bird's eye view of the AI application in all spectrum of geosciences is provided.•The mandatory modular steps of typical Earth AI workflows are summarized.•Twelve grand challenges in Earth AI and potential opportunities are introduced.
Constructed wetlands (CWs) have been proven as a reliable alternative to traditional wastewater treatment technologies. Microorganisms in CWs, as an important component, play a key role in processes ...such as pollutant degradation and nutrient transformation. Therefore, an in-depth analysis of the community structure and diversity of microorganisms, especially for functional microorganisms, in CWs is important to understand its performance patterns and explore optimized strategies. With advances in molecular biotechnology, it is now possible to analyze and study microbial communities and species composition in complex environments. This review performed bibliometric analysis of microbial studies in CWs to evaluate research trends and identify the most studied pollutants. On this basis, the main functional microorganisms of CWs involved in the removal of these pollutants are summarized, and the effects of these pollutants on microbial diversity are investigated. The result showed that the main phylum involved in functional microorganisms in CWs include
,
,
and
. These functional microorganisms can remove pollutants from CWs by catalyzing chemical reactions, biodegradation, biosorption, and supporting plant growth, etc. Regarding microbial alpha diversity, heavy metals and high concentrations of nitrogen and phosphorus significantly reduce microbial richness and diversity, whereas antibiotics can cause large fluctuations in alpha diversity. Overall, this review can provide new ideas and directions for the research of microorganisms in CWs.
The early detection of Diabetic Retinopathy (DR) is critical for diabetics to lower the blindness risks. Many studies represent that Deep Convolutional Neural Network (CNN) based approaches are ...effective to enable automatic DR detection through classifying retinal images of patients. Such approaches usually depend on a very large dataset composed of retinal images with predefined classification labels to support their CNN training. However, in some occasions, it is not so easy to get enough well-labelled images to act as model training samples. At the same time, when a CNN becomes deeper, its training will not only take much longer time, but also be more likely to lead to overfitting, especially on a large training dataset. Therefore, it is meaningful to explore a simpler CNN based approach that is still effective on small datasets to classify retinal images. In this paper, an approach to retinal image classification is proposed based on the integration of multi-scale shallow CNNs. Experiments on public datasets show that, on small datasets, the proposed approach can improve the classification accuracy by 3% compared with current representative integrated CNN learning approaches. On the bigger dataset, the proposed approach can improve the classification accuracy by 3% to 9% compared with other representative approaches such as traditional CNN, LCNN and VGG16noFC. The evaluation also represents that, though the classification accuracy of the proposed approach declines by 6% on the smallest dataset containing only 10% samples of the original dataset, its time cost declines to about 30% of that on the original dataset.
Effect of miR-216a-3p on lung cancer hasn't been investigated. Here, we explored its effects on lung cancer. MiR-216a-3p expression in lung cancer tissues and cells was detected by RT-qPCR. The ...target gene of miR-216a-3p was predicted by bioinformatics and confirmed by luciferase-reporter assay. After transfection, cell viability, migration, invasion, proliferation, and apoptosis were detected by MTT, scratch, transwell, colony formation, and flow cytometry. The expressions of COPB2 and apoptosis-related factors were detected by RT-qPCR or western blot. MiR-216a-3p was low-expressed and COPB2 was high-expressed in lung cancer tissues and cells. MiR-216a-3p targeted COPB2 and regulated its expression. MiR-216a-3p inhibited lung cancer cell viability, migration, invasion, and proliferation, while promoted apoptosis. Effect of miR-216a-3p on lung cancer was reversed by COPB2. MiR-216a-3p regulated proliferation, apoptosis, migration, and invasion of lung cancer cells via targeting COPB2.
Coupling myoelectric and mechanical signals during voluntary muscle contraction is paramount in human-machine interactions. Spatiotemporal differences in the two signals intrinsically arise from the ...muscular excitation-contraction process; however, current methods fail to deliver local electromechanical coupling of the process. Here we present the locally coupled electromechanical interface based on a quadra-layered ionotronic hybrid (named as CoupOn) that mimics the transmembrane cytoadhesion architecture. CoupOn simultaneously monitors mechanical strains with a gauge factor of ~34 and surface electromyogram with a signal-to-noise ratio of 32.2 dB. The resolved excitation-contraction signatures of forearm flexor muscles can recognize flexions of different fingers, hand grips of varying strength, and nervous and metabolic muscle fatigue. The orthogonal correlation of hand grip strength with speed is further exploited to manipulate robotic hands for recapitulating corresponding gesture dynamics. It can be envisioned that such locally coupled electromechanical interfaces would endow cyber-human interactions with unprecedented robustness and dexterity.
How nitrogen (N) supply affects the induced defense of plants remains poorly understood. Here, we investigated the impacts of N supply on the defense induced in maize (Zea mays) against the fall ...armyworm (Spodoptera frugiperda). In the absence of herbivore attack or exogenous jasmonic acid (JA) application, N supply increased plant biomass and enhanced maize nutrient (soluble sugar and amino acid) contents and leaf area fed by S. frugiperda (the feeding leaf area of S. frugiperda larvae in maize supplemented with 52.2 and 156.6 mg/kg of N was 4.08 and 3.83 times that of the control, respectively). When coupled with herbivore attack or JA application, maize supplemented with 52.2 mg/kg of N showed an increased susceptibility to pests, while the maize supplemented with 156.6 mg/kg of N showed an improved defense against pests. The changes in the levels of nutrients, and the emissions of volatile organic compounds (VOCs) caused by N supply could explain the above opposite induced defense in maize. Compared with herbivore attack treatment, JA application enhanced the insect resistance in maize supplemented with 156.6 mg/kg of N more intensely, mainly reflecting a smaller feeding leaf area, which was due to indole emission and two upregulated defensive genes, MPI (maize proteinase inhibitor) and PAL (phenylalanine ammonia-lyase). Hence, the optimal N level and appropriate JA application can enhance plant-induced defense against pests.
Salicylic acid (SA) plays a critical role in allergic reactions of plants to pathogens and acquired systemic resistance. Thus far, although some research has been conducted on the direct effects of ...different concentrations of SA on the chemical defense response of treated plant parts (leaves) after at multiple post-treatments times, few research has reported on the systematic effects of non-treated parts (roots). Therefore, we examined direct and systemic effects of SA concentration and time following foliar application on chemical defense responses in maize variety 5422 with two fully expanded leaves. In the experiments, maize leaves were treated with different SA concentrations of 0.1, 0.5, 1.0, 2.5, 5.0 mM, and then, the presence of defense chemicals and enzymes in treated leaves and non-treated roots was measured at different time points of 3, 12, 24, 48, 72 h following SA foliar application. The results showed that direct and systemic effects of SA treatment to the leaf on chemical defense responses were related to SA concentration and time of measurement after spraying SA. In treated leaves, total phenolics content increased directly by 28.65% at the time point of 12 h following foliar application of 0.5 mM SA. DIMBOA (2,4-dihydroxy-7-methoxy-2H, 1, 4-benzoxazin-3 (4H)-one) content was directly enhanced by 80.56~551.05% after 3~72 h following 0.5~5.0 mM SA treatments. Polyphenol oxidase and superoxide dismutase activities were directly enhanced after 12~72 h following 0.5~5.0 mM SA treatments, whereas peroxidase and catalase activities were increased after 3~24 h following application of 1.0~5.0 mM SA. In non-treated roots, DIMBOA content and polyphenol oxidase activity were enhanced systematically after 3~48 h following 1.0~5.0 mM SA foliar treatments. Superoxide dismutase activities were enhanced after 3~24 h following 0.5~2.5 mM SA applications, but total phenolics content, peroxidase and catalase activity decreased in some particular concentrations or at the different times of measurement in the SA treatment. It can be concluded that SA foliar application at 1.0 and 2.5 mM produces strong chemical defense responses in maize, with the optimal induction time being 24 h following the foliar application.
Discovering the Bayesian network (BN) structure from big datasets containing rich causal relationships is becoming increasingly valuable for modeling and reasoning under uncertainties in many areas ...with big data gathered from sensors due to high volume and fast veracity. Most of the current BN structure learning algorithms have shortcomings facing big data. First, learning a BN structure from the entire big dataset is an expensive task which often ends in failure due to memory constraints. Second, it is quite difficult to select a learner from numerous BN structure learning algorithms to consistently achieve good learning accuracy. Lastly, there is a lack of an intelligent method that merges separately learned BN structures into a well structured BN network. To address these shortcomings, we introduce a novel parallel learning approach called PEnBayes (Parallel Ensemble-based Bayesian network learning). PEnBayes starts with an adaptive data preprocessing phase that calculates the Appropriate Learning Size and intelligently divides a big dataset for fast distributed local structure learning. Then, PEnBayes learns a collection of local BN Structures in parallel using a two-layered weighted adjacent matrix-based structure ensemble method. Lastly, PEnBayes merges the local BN Structures into a global network structure using the structure ensemble method at the global layer. For the experiment, we generate big data sets by simulating sensor data from patient monitoring, transportation, and disease diagnosis domains. The Experimental results show that PEnBayes achieves a significantly improved execution performance with more consistent and stable results compared with three baseline learning algorithms.
The growth of plants is threatened by numerous diseases. Accurate and timely identification of these diseases is crucial to prevent disease spreading. Many deep learning-based methods have been ...proposed for identifying leaf diseases. However, these methods often combine plant, leaf disease, and severity into one category or treat them separately, resulting in a large number of categories or complex network structures. Given this, this paper proposes a novel leaf disease identification network (LDI-NET) using a multi-label method. It is quite special because it can identify plant type, leaf disease and severity simultaneously using a single straightforward branch model without increasing the number of categories and avoiding extra branches. It consists of three modules, i.e., a feature tokenizer module, a token encoder module and a multi-label decoder module. The LDI-NET works as follows: Firstly, the feature tokenizer module is designed to enhance the capability of extracting local and long-range global contextual features by leveraging the strengths of convolutional neural networks and transformers. Secondly, the token encoder module is utilized to obtain context-rich tokens that can establish relationships among the plant, leaf disease and severity. Thirdly, the multi-label decoder module combined with a residual structure is utilized to fuse shallow and deep contextual features for better utilization of different-level features. This allows the identification of plant type, leaf disease, and severity simultaneously. Experiments show that the proposed LDI-NET outperforms the prevalent methods using the publicly available AI challenger 2018 dataset.