Design of vacuum annealing furnace temperature control system based on GA-Fuzzy-PID algorithm.

As is well known, the metal annealing process has the characteristics of heat concentration and rapid heating. Traditional vacuum annealing furnaces use PID control method, which has problems such as high temperature fluctuation, large overshoot, and long response time during the heating and heating process. Based on this situation, some domestic scholars have adopted fuzzy PID control algorithm in the temperature control of vacuum annealing furnaces. Due to the fact that fuzzy rules are formulated through a large amount of on-site temperature data and experience summary, there is a certain degree of subjectivity, which cannot ensure that each rule is optimal. In response to this drawback, the author combined the technical parameters of vacuum annealing furnace equipment, The fuzzy PID temperature control of the vacuum annealing furnace is optimized using genetic algorithm. Through simulation and comparative analysis, it is concluded that the design of the fuzzy PID vacuum annealing furnace temperature control system based on GA optimization is superior to fuzzy PID and traditional PID control in terms of temperature accuracy, rise time, and overshoot control. Finally, it was verified through offline experiments that the fuzzy PID temperature control system based on GA optimization meets the annealing temperature requirements of metal workpieces and can be applied to the temperature control system of vacuum annealing furnaces.

A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations.

The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model's performance improved as the quality of the labels used for training increased.

SWsnn: A Novel Simulator for Spiking Neural Networks.

Spiking neural network (SNN) simulators play an important role in neural system modeling and brain function research. They can help scientists reproduce and explore neuronal activities in brain regions, neuroscience, brain-like computing, and other fields and can also be applied to artificial intelligence, machine learning, and other fields. At present, many simulators using central processing unit (CPU) or graphics processing unit (GPU) have been developed. However, due to the randomness of connections between neurons and spiking events in SNN simulation, this causes a lot of memory access time. To alleviate this problem, we developed an SNN simulator SWsnn based on the new Sunway SW26010pro processor. The SW26010pro processor consists of six core groups, each with 16 MB of local data memory (LDM). LDM has the characteristics of high-speed read and write, which is suitable for performing simulation tasks similar to SNNs. Experimental results show that SWsnn runs faster than other mainstream GPU-based simulators when simulating a certain scale of neural network, showing a strong performance advantage. To conduct larger scale simulations, SWsnn designed a simulation computation based on a large shared model of Sunway processor and developed a multiprocessor version of SWsnn based on this mode, achieving larger scale SNN simulations.

zPoseScore model for accurate and robust protein-ligand docking pose scoring in CASP15.

We introduce a deep learning-based ligand pose scoring model called zPoseScore for predicting protein-ligand complexes in the 15th Critical Assessment of Protein Structure Prediction (CASP15). Our contributions are threefold: first, we generate six training and evaluation data sets by employing advanced data augmentation and sampling methods. Second, we redesign the "zFormer" module, inspired by AlphaFold2's Evoformer, to efficiently describe protein-ligand interactions. This module enables the extraction of protein-ligand paired features that lead to accurate predictions. Finally, we develop the zPoseScore framework with zFormer for scoring and ranking ligand poses, allowing for atomic-level protein-ligand feature encoding and fusion to output refined ligand poses and ligand per-atom deviations. Our results demonstrate excellent performance on various testing data sets, achieving Pearson's correlation R = 0.783 and 0.659 for ranking docking decoys generated based on experimental and predicted protein structures of CASF-2016 protein-ligand complexes. Additionally, we obtain an averaged local distance difference test (lDDT pli = 0.558) of AIchemy LIG2 in CASP15 for de novo protein-ligand complex structure predictions. Detailed analysis shows that accurate ligand binding site prediction and side-chain orientation are crucial for achieving better prediction performance. Our proposed model is one of the most accurate protein-ligand pose prediction models and could serve as a valuable tool in small molecule drug discovery.

A Federated Attention-Based Multimodal Biometric Recognition Approach in IoT.

The rise of artificial intelligence applications has led to a surge in Internet of Things (IoT) research. Biometric recognition methods are extensively used in IoT access control due to their convenience. To address the limitations of unimodal biometric recognition systems, we propose an attention-based multimodal biometric recognition (AMBR) network that incorporates attention mechanisms to extract biometric features and fuse the modalities effectively. Additionally, to overcome issues of data privacy and regulation associated with collecting training data in IoT systems, we utilize Federated Learning (FL) to train our model This collaborative machine-learning approach enables data parties to train models while preserving data privacy. Our proposed approach achieves 0.68%, 0.47%, and 0.80% Equal Error Rate (EER) on the three VoxCeleb1 official trial lists, performs favorably against the current methods, and the experimental results in FL settings illustrate the potential of AMBR with an FL approach in the multimodal biometric recognition scenario.

A Localized High-Concentration Water/Organic Hybrid Electrolyte for 2.5 V Li4Ti5O12/LiMn2O4 Batteries.

The "solvent-in-salt" electrolytes for an aqueous system, including "water-in-salt" electrolytes and "bisolvent-in-salt" electrolytes, have shown significantly improved electrochemical stability toward low-voltage anodes and high-voltage cathodes. However, the heavy use of salt raises concerns of high cost, high viscosity, inferior wettability, and poor low-temperature performance. Herein, a "localized bisolvent-in-salt electrolyte" is proposed by introducing 1,1,2,2-tetrafluoroethyl-2,2,3,3-tetrafluoropropyl ether (TTE) as the diluent to the high-concentration water/sulfolane hybrid (BSiS-SL) electrolytes, forming a ternary solvent-based electrolyte, Li(H2O)0.9SL1.3·TTE1.3 (HS-TTE). The introduction of TTE dilutes the compact ionic clusters, while the original primary Li+ solvation structure remains, and in the meantime, boosts the formation of a robust solid electrolyte interphase. As a result, a wide electrochemically stable window of 4.4 V is achieved. In comparison with the bisolvent BSiS-SL system, the trisolvent HS-TTE electrolyte exhibits a low salt concentration of 2.1 mol kg-1, resulting in drastically reduced viscosity, superb separator wettability, and largely improved low-temperature performance. The constructed 2.5 V Li4Ti5O12/LiMn2O4 cell shows an excellent capacity retention of 80.7% after 800 cycles, and the cell can even work at -30 °C. With these extraordinary advantages, the fundamental designing strategy of the HS-TTE electrolyte developed in this work can promote the practical applications of solvent-in-salt electrolytes.

Hierarchical Electrode Architecture Enabling Ultrahigh-Capacity LiFePO4 Cathodes with Low Tortuosity.

Thickening electrodes are expected to increase the energy density of batteries. Unfortunately, the manufacturing issues, sluggish electrolyte infiltration, and restrictions on electron/ion transport seriously hamper the development of thick electrodes. In this work, an ultrathick LiFePO4 (LFP) electrode with hierarchically vertical microchannels and porous structures (I-LFP) is rationally designed by combining the template method and the mechanical channel-making method. By using ultrasonic transmission mapping technology, it is proven that the open and vertical microchannels and interconnected pores can successfully overcome the electrolyte infiltration difficulty of conventional thick electrodes. Meanwhile, both the electrochemical and simulation characterizations reveal the fast ion transport kinetics and low tortuosity (1.44) in the I-LFP electrode. As a result, the I-LFP electrode delivers marked improvements in rate performance and cycling stability even under a high areal loading of 180 mg cm-2. Moreover, according to the results of operando optical fiber sensors, the stress accumulation in the I-LFP electrode is effectively alleviated, which further confirms the improvement of mechanical stability.

1,3-Dimethyl-2-imidazolidinone: an ideal electrolyte solvent for high-performance Li-O2 battery with pretreated Li anode.

Electrolytes are widely considered as a key component in Li-O2 batteries (LOBs) because they greatly affect the discharge-charge reaction kinetics and reversibility. Herein, we report that 1,3-dimethyl-2-imidazolidinone (DMI) is an excellent electrolyte solvent for LOBs. Comparing with conventional ether and sulfone based electrolytes, it has higher Li2O2 and Li2CO3 solubility, which on the one hand depresses cathode passivation during discharge, and on the other hand promotes the liquid-phase redox shuttling during charge, and consequently lowers the overpotential and improves the cyclability of the battery. However, despite the many advantages at the cathode side, DMI is not stable with bare Li anode. Thus, we have developed a pretreatment method to grow a protective artificial solid-state electrolyte interface (SEI) to prevent the unfavorable side-reactions on Li. The SEI film was formed via the reaction between fluorine-rich organic reagents and Li metal. It is composed of highly Li+-conducting LixBOy, LiF, LixNOy, Li3N particles and some organic compounds, in which LixBOy serves as a binder to enhance its mechanical strength. With the protective SEI, the coulombic efficiency of Li plating/stripping in DMI electrolyte increased from 20% to 98.5% and the fixed capacity cycle life of the assembled LOB was elongated to 205 rounds, which was almost fivefold of the cycle life in dimethyl sulfoxide (DMSO) or tetraglyme (TEGDME) based electrolytes. Our work demonstrates that molecular polarity and ionic solvation structure are the primary issues to be considered when designing high performance Li-O2 battery electrolytes, and cross-linked artificial SEI is effective in improving the anodic stability.

Inter-Residue Distance Prediction From Duet Deep Learning Models.

Residue distance prediction from the sequence is critical for many biological applications such as protein structure reconstruction, protein-protein interaction prediction, and protein design. However, prediction of fine-grained distances between residues with long sequence separations still remains challenging. In this study, we propose DuetDis, a method based on duet feature sets and deep residual network with squeeze-and-excitation (SE), for protein inter-residue distance prediction. DuetDis embraces the ability to learn and fuse features directly or indirectly extracted from the whole-genome/metagenomic databases and, therefore, minimize the information loss through ensembling models trained on different feature sets. We evaluate DuetDis and 11 widely used peer methods on a large-scale test set (610 proteins chains). The experimental results suggest that 1) prediction results from different feature sets show obvious differences; 2) ensembling different feature sets can improve the prediction performance; 3) high-quality multiple sequence alignment (MSA) used for both training and testing can greatly improve the prediction performance; and 4) DuetDis is more accurate than peer methods for the overall prediction, more reliable in terms of model prediction score, and more robust against shallow multiple sequence alignment (MSA).

Tuning the Electrolyte Solvation Structure via a Nonaqueous Co-Solvent to Enable High-Voltage Aqueous Lithium-Ion Batteries.

"Water-in-salt" electrolytes have significantly expanded the electrochemical stability window of the aqueous electrolytes from 1.23 to 3 V, making highly safe 3.0 V aqueous Li-ion batteries possible. However, the awkward cathodic limit located at 1.9 V (versus Li+/Li) and the high cost of the expensive salts hinder the practical applications. In this work, an ideal "bisolvent-in-salt" electrolyte is reported to tune the electrolyte solvation structure via introducing sulfolane as the co-solvent, which significantly enhances the cathodic limit of water to 1.0 V (versus Li+/Li) at a significantly reduced salt concentration of 5.7 mol kg-1. Due to the competitive coordination of sulfolane, water molecules that should be in the primary solvation sheath of Li+ are partly substituted by the electrochemically stable sulfolane, significantly decreasing the hydrogen evolution. Meanwhile, the unique electrolyte structures enable the formation and stabilization of a robust solid electrolyte interphase. As a result, a 2.4 V LiMn2O4/Li4Ti5O12 full cell with a high energy density of 128 Wh kg-1 is realized. The hybrid water/sulfolane electrolytes provide a brand new strategy for designing aqueous electrolytes with an expanded electrochemical stability window at a low salt concentration.

Improving protein-ligand docking and screening accuracies by incorporating a scoring function correction term.

Scoring functions are important components in molecular docking for structure-based drug discovery. Traditional scoring functions, generally empirical- or force field-based, are robust and have proven to be useful for identifying hits and lead optimizations. Although multiple highly accurate deep learning- or machine learning-based scoring functions have been developed, their direct applications for docking and screening are limited. We describe a novel strategy to develop a reliable protein-ligand scoring function by augmenting the traditional scoring function Vina score using a correction term (OnionNet-SFCT). The correction term is developed based on an AdaBoost random forest model, utilizing multiple layers of contacts formed between protein residues and ligand atoms. In addition to the Vina score, the model considerably enhances the AutoDock Vina prediction abilities for docking and screening tasks based on different benchmarks (such as cross-docking dataset, CASF-2016, DUD-E and DUD-AD). Furthermore, our model could be combined with multiple docking applications to increase pose selection accuracies and screening abilities, indicating its wide usage for structure-based drug discoveries. Furthermore, in a reverse practice, the combined scoring strategy successfully identified multiple known receptors of a plant hormone. To summarize, the results show that the combination of data-driven model (OnionNet-SFCT) and empirical scoring function (Vina score) is a good scoring strategy that could be useful for structure-based drug discoveries and potentially target fishing in future.

Boosting the predictive performance with aqueous solubility dataset curation.

Intrinsic solubility is a critical property in pharmaceutical industry that impacts in-vivo bioavailability of small molecule drugs. However, solubility prediction with Artificial Intelligence(AI) are facing insufficient data, poor data quality, and no unified measurements for AI and physics-based approaches. We collect 7 aqueous solubility datasets, and present a dataset curation workflow. Evaluating the curated data with two expanded deep learning methods, improved RMSE scores on all curated thermodynamic datasets are observed. We also compare expanded Chemprop enhanced with curated data and state-of-art physics-based approach using pearson and spearman correlation coefficients. A similar performance on pearson with 0.930 and spearman with 0.947 from expanded Chemprop is achieved. A steadily improved pearson and spearman values with increasing data points are also illustrated. Besides that, the computation advantage of AI models enables quick evaluation of a large set of molecules during the hit identification or lead optimization stages, which helps further decision making within the time cycle at drug discovery stage.

Data Mining to Atmospheric Corrosion Process Based on Evidence Fusion.

An electrical resistance sensor-based atmospheric corrosion monitor was employed to study the carbon steel corrosion in outdoor atmospheric environments by recording dynamic corrosion data in real-time. Data mining of collected data contributes to uncovering the underlying mechanism of atmospheric corrosion. In this study, it was found that most statistical correlation coefficients do not adapt to outdoor coupled corrosion data. In order to deal with online coupled data, a new machine learning model is proposed from the viewpoint of information fusion. It aims to quantify the contribution of different environmental factors to atmospheric corrosion in different exposure periods. Compared to the commonly used machine learning models of artificial neural networks and support vector machines in the corrosion research field, the experimental results demonstrated the efficiency and superiority of the proposed model on online corrosion data in terms of measuring the importance of atmospheric factors and corrosion prediction accuracy.

A Supramolecular Complex of C60 -S with High-Density Active Sites as a Cathode for Lithium-Sulfur Batteries.

The well-known "shuttle effect" of the intermediate lithium polysulfides (LiPSs) and low sulfur utilization hinder the practical application of lithium-sulfur (Li-S) batteries. Herein, we describe a novel C60 -S supramolecular complex with high-density active sites for LiPS adsorption that was formed by a simple one-step process as a cathode material for Li-S batteries. Benefiting from the cocrystal structure, 100 % of the C60 molecules in the complex can offer active sites to adsorb LiPSs and catalyze their conversion. Furthermore, the lithiated C60 cores promote internal ion transport inside the composite cathode. At a low electrolyte/sulfur ratio of 5 µL mg-1 , the C60 -S cathode with a sulfur loading of 4 mg cm-2 exhibited a high capacity of 809 mAh g-1 (3.2 mAh cm-2 ). The development of the C60 -S supramolecular complex will inspire the invention of a new family of S/fullerenes as cathodes for high-performance Li-S batteries and extend the application of fullerenes.

Counting Kmers for Biological Sequences at Large Scale.

Counting the abundance of all the distinct kmers in biological sequence data is a fundamental step in bioinformatics. These applications include de novo genome assembly, error correction, etc. With the development of sequencing technology, the sequence data in a single project can reach Petabyte-scale or Terabyte-scale nucleotides. Counting demand for the abundance of these sequencing data is beyond the memory and computing capacity of single computing node, and how to process it efficiently is a challenge on a high-performance computing cluster. As such, we propose SWAPCounter, a highly scalable distributed approach for kmer counting. This approach is embedded with an MPI streaming I/O module for loading huge data set at high speed, and a counting bloom filter module for both memory and communication efficiency. By overlapping all the counting steps, SWAPCounter achieves high scalability with high parallel efficiency. The experimental results indicate that SWAPCounter has competitive performance with two other tools on shared memory environment, KMC2, and MSPKmerCounter. Moreover, SWAPCounter also shows the highest scalability under strong scaling experiments. In our experiment on Cetus supercomputer, SWAPCounter scales to 32,768 cores with 79% parallel efficiency (using 2048 cores as baseline) when processing 4 TB sequence data of 1000 Genomes. The source code of SWAPCounter is publicly available at https://github.com/mengjintao/SWAPCounter.

Intrinsically Optimizing Charge Transfer via Tuning Charge/Discharge Mode for Lithium-Oxygen Batteries.

Lithium-oxygen batteries have an ultrahigh theoretical energy density, almost ten times higher than lithium-ion batteries. The poor conductivity of the discharge product Li2 O2 , however, severely raises the charge overpotential and pulls down the cyclability. Here, a simple and effective strategy is presented for regular formation of lithium vacancies in the discharge product via tuning charge/discharge mode, and their effects on the charge transfer behavior. The effects of the discharge current density on the lithium vacancies, ionic conductivity, and electronic conductivity of the discharge product Li2 O2 are systematically investigated via electron spin resonance, spin-alignment echo nuclear magnetic resonance, and tungsten nanomanipulators, respectively. The study by density functional theory indicates that the lithium vacancies in Li2 O2 generated during the discharge process are highly dependent on the current density. High current can induce a high vacancy density, which enhances the electronic conductivity and reduces the overpotential. Meanwhile, with increasing discharge current, the morphology of the Li2 O2 changes from microtoroids to thin nanoplatelets, effectively shortening the charge transfer distance and improving the cycling performance. The Li2 O2 grown in fast discharge mode is more easily decomposed in the following charging process. The lithium-oxygen battery cycling in fast-discharge/slow-charge mode exhibits low overpotential and long cycle life.

Application of An Electrical Resistance Sensor-Based Automated Corrosion Monitor in the Study of Atmospheric Corrosion.

An automated corrosion monitor, named the Internet of Things atmospheric corrosion monitor (IoT ACM) has been developed. IoT ACM is based on electrical resistance sensor and enables accurate and continuous measurement of corrosion data of metallic materials. The objective of this research is to study the characteristics of atmospheric corrosion by analyzing the acquired corrosion data from IoT ACM. Employing data processing and data analysis methods to research the acquired corrosion data of steel, the atmospheric corrosion characteristics implied in the corrosion data can be discovered. Comparing the experiment results with the phenomenon of previous laboratory experiment and conclusions of previously published reports, the research results are tested and verified. The experiment results show that the change regulation of atmospheric corrosion data in the actual environment is reasonable and normal. The variation of corrosion depth is obviously influenced by relative humidity, temperature and part of air pollutants. It can be concluded that IoT ACM can be well applied to the conditions of atmospheric corrosion monitoring of metallic materials and the study of atmospheric corrosion by applying IoT ACM is effective and instructive under an actual atmospheric environment.

SWAP-Assembler: scalable and efficient genome assembly towards thousands of cores.

BACKGROUND: There is a widening gap between the throughput of massive parallel sequencing machines and the ability to analyze these sequencing data. Traditional assembly methods requiring long execution time and large amount of memory on a single workstation limit their use on these massive data. RESULTS: This paper presents a highly scalable assembler named as SWAP-Assembler for processing massive sequencing data using thousands of cores, where SWAP is an acronym for Small World Asynchronous Parallel model. In the paper, a mathematical description of multi-step bi-directed graph (MSG) is provided to resolve the computational interdependence on merging edges, and a highly scalable computational framework for SWAP is developed to automatically preform the parallel computation of all operations. Graph cleaning and contig extension are also included for generating contigs with high quality. Experimental results show that SWAP-Assembler scales up to 2048 cores on Yanhuang dataset using only 26 minutes, which is better than several other parallel assemblers, such as ABySS, Ray, and PASHA. Results also show that SWAP-Assembler can generate high quality contigs with good N50 size and low error rate, especially it generated the longest N50 contig sizes for Fish and Yanhuang datasets. CONCLUSIONS: In this paper, we presented a highly scalable and efficient genome assembly software, SWAP-Assembler. Compared with several other assemblers, it showed very good performance in terms of scalability and contig quality. This software is available at: https://sourceforge.net/projects/swapassembler.