Underdetermined Blind Source Separation of Audio Signals for Group Reared Pigs Based on Sparse Component Analysis.

In order to solve the problem of difficult separation of audio signals collected in pig environments, this study proposes an underdetermined blind source separation (UBSS) method based on sparsification theory. The audio signals obtained by mixing the audio signals of pigs in different states with different coefficients are taken as observation signals, and the mixing matrix is first estimated from the observation signals using the improved AP clustering method based on the "two-step method" of sparse component analysis (SCA), and then the audio signals of pigs are reconstructed by L1-paradigm separation. Five different types of pig audio are selected for experiments to explore the effects of duration and mixing matrix on the blind source separation algorithm by controlling the audio duration and mixing matrix, respectively. With three source signals and two observed signals, the reconstructed signal metrics corresponding to different durations and different mixing matrices perform well. The similarity coefficient is above 0.8, the average recovered signal-to-noise ratio is above 8 dB, and the normalized mean square error is below 0.02. The experimental results show that different audio durations and different mixing matrices have certain effects on the UBSS algorithm, so the recording duration and the spatial location of the recording device need to be considered in practical applications. Compared with the classical UBSS algorithm, the proposed algorithm outperforms the classical blind source separation algorithm in estimating the mixing matrix and separating the mixed audio, which improves the reconstruction quality.

Research on Pig Sound Recognition Based on Deep Neural Network and Hidden Markov Models.

In order to solve the problem of low recognition accuracy of traditional pig sound recognition methods, deep neural network (DNN) and Hidden Markov Model (HMM) theory were used as the basis of pig sound signal recognition in this study. In this study, the sounds made by 10 landrace pigs during eating, estrus, howling, humming and panting were collected and preprocessed by Kalman filtering and an improved endpoint detection algorithm based on empirical mode decomposition-Teiger energy operator (EMD-TEO) cepstral distance. The extracted 39-dimensional mel-frequency cepstral coefficients (MFCCs) were then used as a dataset for network learning and recognition to build a DNN- and HMM-based sound recognition model for pig states. The results show that in the pig sound dataset, the recognition accuracy of DNN-HMM reaches 83%, which is 22% and 17% higher than that of the baseline models HMM and GMM-HMM, and possesses a better recognition effect. In a sub-dataset of the publicly available dataset AudioSet, DNN-HMM achieves a recognition accuracy of 79%, which is 8% and 4% higher than the classical models SVM and ResNet18, respectively, with better robustness.

Research on the Recognition and Tracking of Group-Housed Pigs' Posture Based on Edge Computing.

The existing algorithms for identifying and tracking pigs in barns generally have a large number of parameters, relatively complex networks and a high demand for computational resources, which are not suitable for deployment in embedded-edge nodes on farms. A lightweight multi-objective identification and tracking algorithm based on improved YOLOv5s and DeepSort was developed for group-housed pigs in this study. The identification algorithm was optimized by: (i) using a dilated convolution in the YOLOv5s backbone network to reduce the number of model parameters and computational power requirements; (ii) adding a coordinate attention mechanism to improve the model precision; and (iii) pruning the BN layers to reduce the computational requirements. The optimized identification model was combined with DeepSort to form the final Tracking by Detecting algorithm and ported to a Jetson AGX Xavier edge computing node. The algorithm reduced the model size by 65.3% compared to the original YOLOv5s. The algorithm achieved a recognition precision of 96.6%; a tracking time of 46 ms; and a tracking frame rate of 21.7 FPS, and the precision of the tracking statistics was greater than 90%. The model size and performance met the requirements for stable real-time operation in embedded-edge computing nodes for monitoring group-housed pigs.

Antifouling Slippery Surface against Marine Biofouling.

Titanium and its alloys have become the most excellent structure materials for naval seawater pipelines due to their high strength and good corrosion resistance. However, marine biofouling poses a serious threat to titanium alloy piping systems because of their good biocompatibility. Recently, the biomimetic antifouling coating, a novel antifouling method, has received great attention. Here, based on this biomimetic idea, we develop a nontoxic antifouling slippery surface (AFSS) using silicone oil, silane coupling agent, nanosilica, nanoceramic coating, epoxy resin, and capsaicin. The developed AFSS has excellent slippery performance for various droplets, good durability, and a superior self-cleaning property. Additionally, the antifouling performance of the AFSS was significantly enhanced, as confirmed by the reduced adhesion of proteins (70.7%), bacteria (97.2%), and algae (97.7%) compared to the ordinary titanium alloy. With these excellent properties, the AFSS was expected to be a promising candidate for protecting titanium alloy piping systems from marine biofouling.

Evaluation of the Effectiveness of Derived Features of AlphaFold2 on Single-Sequence Protein Binding Site Prediction.

Though AlphaFold2 has attained considerably high precision on protein structure prediction, it is reported that directly inputting coordinates into deep learning networks cannot achieve desirable results on downstream tasks. Thus, how to process and encode the predicted results into effective forms that deep learning models can understand to improve the performance of downstream tasks is worth exploring. In this study, we tested the effects of five processing strategies of coordinates on two single-sequence protein binding site prediction tasks. These five strategies are spatial filtering, the singular value decomposition of a distance map, calculating the secondary structure feature, and the relative accessible surface area feature of proteins. The computational experiment results showed that all strategies were suitable and effective methods to encode structural information for deep learning models. In addition, by performing a case study of a mutated protein, we showed that the spatial filtering strategy could introduce structural changes into HHblits profiles and deep learning networks when protein mutation happens. In sum, this work provides new insight into the downstream tasks of protein-molecule interaction prediction, such as predicting the binding residues of proteins and estimating the effects of mutations.

Recent Advances in Zinc Hydroxystannate-Based Flame Retardant Polymer Blends.

During the combustion of polymeric materials, plenty of heat, smoke, and toxic gases are produced that may cause serious harm to human health. Although the flame retardants such as halogen- and phosphorus-containing compounds can inhibit combustion, they cannot effectively reduce the release of toxic fumes. Zinc hydroxystannate (ZHS, ZnSn(OH)6) is an environmentally friendly flame retardant that has attracted extensive interest because of its high efficiency, safety, and smoke suppression properties. However, using ZHS itself may not contribute to the optimal flame retardant effect, which is commonly combined with other flame retardants to achieve more significant efficiency. Few articles systematically review the recent development of ZHS in the fire safety field. This review aims to deliver an insight towards further direction and advancement of ZHS in flame retardant and smoke suppression for multiple polymer blends. In addition, the fire retarded and smoke suppression mechanism of ZHS will be demonstrated and discussed in depth.

Fabrication of dual anti-corrosive polyaniline microcapsules via Pickering emulsion for active corrosion protection of steel.

A novel kind of inhibitor-loaded polyaniline (PANI) microcapsule was prepared by Pickering emulsion photopolymerization using polyaniline particles as the Pickering emulsifier. In our strategy, water-dispersible polyaniline nanoparticles were firstly synthesized using a micelle template method and used to stabilize oil-in-water emulsions, in which the oil phase contained photo-crosslinkable and pH sensitive monomers and a photo-initiator. Under UV light, the pH-responsive monomers underwent photo-polymerization and crosslinking and converted to microcapsule shells. During this process, polyaniline nanoparticles were trapped in the microcapsule shells, leading to the formation of PANI microcapsules. The structure and morphology of the synthesized PANI microcapsules were analyzed using FTIR spectroscopy, SEM, and EDX mapping. The inhibitor (mercaptobenzothiazole, MBT) was subsequently incorporated into the PANI microcapsule as a functional core and demonstrated pH-sensitive releasing behavior. With the anti-corrosive PANI as the microcapsule wall and the inhibitor MBT as the core, the as-prepared MBT loaded PANI (MBT@PANI) microcapsule could afford dual corrosion protection, allowing smart protection of metals when exposed to corrosive conditions. The MBT@PANI microcapsules were embedded in UV-cured coating for protecting steel. The corrosion protection performance of the coating with MBT@PANI microcapsules was evaluated using the electrochemical impedance spectroscopy technique and salt spray test, which demonstrated the synergistic inhibition effect of the PANI wall and the loaded MBT in improving anti-corrosion performance of the coating.

An Integrative Segmentation Framework for Cell Nucleus of Fluorescence Microscopy.

Nucleus segmentation of fluorescence microscopy is a critical step in quantifying measurements in cell biology. Automatic and accurate nucleus segmentation has powerful applications in analyzing intrinsic characterization in nucleus morphology. However, existing methods have limited capacity to perform accurate segmentation in challenging samples, such as noisy images and clumped nuclei. In this paper, inspired by the idea of cascaded U-Net (or W-Net) and its remarkable performance improvement in medical image segmentation, we proposed a novel framework called Attention-enhanced Simplified W-Net (ASW-Net), in which a cascade-like structure with between-net connections was used. Results showed that this lightweight model could reach remarkable segmentation performance in the BBBC039 testing set (aggregated Jaccard index, 0.90). In addition, our proposed framework performed better than the state-of-the-art methods in terms of segmentation performance. Moreover, we further explored the effectiveness of our designed network by visualizing the deep features from the network. Notably, our proposed framework is open source.

A selection pressure landscape for 870 human polygenic traits.

Characterizing the natural selection of complex traits is important for understanding human evolution and both biological and pathological mechanisms. We leveraged genome-wide summary statistics for 870 polygenic traits and attempted to quantify signals of selection on traits of different forms in European ancestry across four periods in human history and evolution. We found that 88% of these traits underwent polygenic change in the past 2,000-3,000 years. Recent selection was associated with ancient selection signals in the same trait. Traits related to pigmentation, body measurement and nutritional intake exhibited strong selection signals across different time scales. Our findings are limited by our use of exclusively European data and the use of genome-wide association study data, which identify associations between genetic variants and phenotypes that may not be causal. In sum, we provide an overview of signals of selection on human polygenic traits and their characteristics across human evolution, based on a European subset of human genetic diversity. These findings could serve as a foundation for further populational and medical genetic studies.

Large-area fabrication of superhydrophobic micro-conical pillar arrays on various metallic substrates.

Superhydrophobic micro-conical pillar arrays have huge application prospects, from anti-icing to oil/water separation, corrosion resistance, and water droplet manipulation. However, there is still a lack of versatile methods with high processing efficiency to fabricate superhydrophobic micro-conical pillar arrays on various metallic substrates. Herein, a nanosecond laser ablation technology with versatility and high processing efficiency was developed to fabricate large-area superhydrophobic micro-conical pillar arrays. The simulation and experiments indicated that the height and the pillar inclination angle of micro-conical pillars could be easily controlled by adjusting the nanosecond laser parameters or the tilted angles of metallic substrates. The fabricated superhydrophobic micro-conical pillar arrays not only showed good mechanical robustness and chemical stability but also easily reduced the contact time for an impinging water droplet, showing potential application prospects in anti-icing from freezing rain. This kind of method with versatility and high processing efficiency will promote the practical applications of superhydrophobic micro-conical arrays.

Integrative enrichment analysis of gene expression based on an artificial neuron.

BACKGROUND: Huntington's disease is a kind of chronic progressive neurodegenerative disease with complex pathogenic mechanisms. To data, the pathogenesis of Huntington's disease is still not fully understood, and there has been no effective treatment. The rapid development of high-throughput sequencing technologies makes it possible to explore the molecular mechanisms at the transcriptome level. Our previous studies on Huntington's disease have shown that it is difficult to distinguish disease-associated genes from non-disease genes. Meanwhile, recent progress in bio-medicine shows that the molecular origin of chronic complex diseases may not exist in the diseased tissue, and differentially expressed genes between different tissues may be helpful to reveal the molecular origin of chronic diseases. Therefore, developing integrative analysis computational methods for the multi-tissues gene expression data, exploring the relationship between differentially expressed genes in different tissues and the disease, can greatly accelerate the molecular discovery process. METHODS: For analysis of the intra- and inter- tissues' differentially expressed genes, we designed an integrative enrichment analysis method based on an artificial neuron (IEAAN). Firstly, we calculated the differential expression scores of genes which are seen as features of the corresponding gene, using fold-change approach with intra- and inter- tissues' gene expression data. Then, we weighted sum all the differential expression scores through a sigmoid function to get differential expression enrichment score. Finally, we ranked the genes according to the enrichment score. Top ranking genes are supposed to be the potential disease-associated genes. RESULTS: In this study, we conducted large amounts of experiments to analyze the differentially expressed genes of intra- and inter- tissues. Experimental results showed that genes differentially expressed between different tissues are more likely to be Huntington's disease-associated genes. Five disease-associated genes were selected out in this study, two of which have been reported to be implicated in Huntington's disease. CONCLUSIONS: We proposed a novel integrative enrichment analysis method based on artificial neuron (IEAAN), which displays better prediction precision of disease-associated genes in comparison with the state-of-the-art statistical-based methods. Our comprehensive evaluation suggests that genes differentially expressed between striatum and liver tissues of health individuals are more likely to be Huntington's disease-associated genes.

Predictive performance of dynamic arterial elastance for arterial pressure response to fluid expansion in mechanically ventilated hypotensive adults: a systematic review and meta-analysis of observational studies.

BACKGROUND: Dynamic arterial elastance (Eadyn) has been extensively considered as a functional parameter of arterial load. However, conflicting evidence has been obtained on the ability of Eadyn to predict mean arterial pressure (MAP) changes after fluid expansion. This meta-analysis sought to assess the predictive performance of Eadyn for the MAP response to fluid expansion in mechanically ventilated hypotensive patients. METHODS: We systematically searched electronic databases through November 28, 2020, to retrieve studies that evaluated the association between Eadyn and fluid expansion-induced MAP increases in mechanically ventilated hypotensive adults. Given the diverse threshold value of Eadyn among the studies, we only reported the area under the hierarchical summary receiver operating characteristic curve (AUHSROC) as the primary measure of diagnostic accuracy. RESULTS: Eight observational studies that included 323 patients with 361 fluid expansions met the eligibility criteria. The results showed that Eadyn was a good predictor of MAP increases in response to fluid expansion, with an AUHSROC of 0.92 [95% confidence interval (CI) 0.89 to 0.94]. Six studies reported the cut-off value of Eadyn, which ranged from 0.65 to 0.89. The cut-off value of Eadyn was nearly conically symmetrical, most data were centred between 0.7 and 0.8, and the mean and median values were 0.77 and 0.75, respectively. The subgroup analyses indicated that the AUHSROC was slightly higher in the intensive care unit (ICU) patients (0.96; 95% CI 0.94 to 0.98) but lower in the surgical patients in the operating room (0.72; 95% CI 0.67 to 0.75). The results indicated that the fluid type and measurement technique might not affect the diagnostic accuracy of Eadyn. Moreover, the AUHSROC for the sensitivity analysis of prospective studies was comparable to that in the primary analysis. CONCLUSIONS: Eadyn exhibits good performance for predicting MAP increases in response to fluid expansion in mechanically ventilated hypotensive adults, especially in the ICU setting.

Integrative analysis of cross-modal features for the prognosis prediction of clear cell renal cell carcinoma.

MOTIVATION: As a highly heterogeneous disease, clear cell renal cell carcinoma (ccRCC) has quite variable clinical behaviors. The prognostic biomarkers play a crucial role in stratifying patients suffering from ccRCC to avoid over- and under-treatment. Researches based on hand-crafted features and single-modal data have been widely conducted to predict the prognosis of ccRCC. However, these experience-dependent methods, neglecting the synergy among multimodal data, have limited capacity to perform accurate prediction. Inspired by complementary information among multimodal data and the successful application of convolutional neural networks (CNNs) in medical image analysis, a novel framework was proposed to improve prediction performance. RESULTS: We proposed a cross-modal feature-based integrative framework, in which deep features extracted from computed tomography/histopathological images by using CNNs were combined with eigengenes generated from functional genomic data, to construct a prognostic model for ccRCC. Results showed that our proposed model can stratify high- and low-risk subgroups with significant difference (P-value < 0.05) and outperform the predictive performance of those models based on single-modality features in the independent testing cohort [C-index, 0.808 (0.728-0.888)]. In addition, we also explored the relationship between deep image features and eigengenes, and make an attempt to explain deep image features from the view of genomic data. Notably, the integrative framework is available to the task of prognosis prediction of other cancer with matched multimodal data. AVAILABILITY AND IMPLEMENTATION: https://github.com/zhang-de-lab/zhang-lab? from=singlemessage. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The correlation between surface hydrophobicity and adherence of Bifidobacterium strains from centenarians' faeces.

To develop food-grade bifidobacteria micro-ecologics, screening for Bifidobacteria strains which can adhere to intestinal epithelial cells was finished. Twenty-three bifidobacterial strains tested were isolated from centenarians in Bama country, the fifth long-lived district in the world. Surface hydrophobicity and adherence capability to intestinal epithelial cells in vitro of bifidobacteria were simultaneously investigated for the first time. It has been demonstrated that all the strains exhibited adhesive properties to some extent using intestinal Caco-2 cell line in in vitro model. It could be conclude that the higher hydrophobic strains the stronger adhesive capability. The highest value of hydrophobicity (37.24+/-1.45% and 32.06+/-1.21%) was obtained for strains H-10 and I-6, respectively; correspondingly, the strongest adherence ability (49.47+/-4.88/cell and 47.33+/-2.72/cell) was achieved, respectively. Correlation between surface hydrophobicity and adherence ability of different Bifidobacterium strains including polynomial regression equation (R2=0.78) had been achieved. The present study provided a liable and effective method for screening bifidobacteria with the ability to adhere to intestinal epithelial cells.