City College of Dongguan University of Technology

Abstract Since 2004, the design of high entropy alloys (HEAs) has generated significant interest within the materials science community due to their exceptional structural and functional properties. By incorporating multiple principal elements into a common lattice, it is possible to create a single‐phase crystal with a highly distorted lattice. This unique feature enables HEAs to offer a promising combination of mechanical and physical properties that are not typically observed in conventional alloys. In this article, an extensive overview of multifunctional HEAs that exhibit severe lattice distortion is provided, covering the theoretical models that are developed to understand lattice distortion, the experimental and computational methods employ to characterize lattice distortion, and most importantly, the impact of severe lattice distortion on the mechanical, physical and electrochemical properties of HEAs. Through this review, it is hoped to stimulate further research into the study of distorted lattices in crystalline solids.

Self-supporting Fe 2 O 3 –CeO 2 nano-heterojunction electrodes with rich oxygen vacancies present high catalytic performance for oxygen evolution reaction, where defect-engineering promotes the interfacial interaction and activates the lattice oxygens.

Bacteriophages are viruses that infect bacteria or archaea. Understanding the diverse and intricate genomic architectures of phages is essential to study microbial ecosystems and develop phage therapy strategies. However, the existing phage databases are short of meticulous annotations. To this end, we propose PhageScope (https://phagescope.deepomics.org), an online phage database with comprehensive annotations. PhageScope harbors a collection of 873 718 phage sequences from various sources. Applying fifteen state-of-the-art tools to perform systematic annotations and analyses, PhageScope provides annotations on genome completeness, host range, lifestyle information, taxonomy classification, nine types of structural and functional genetic elements, and three types of comparative genomic studies for curated phages. Additionally, PhageScope incorporates automatic analyses and visualizations for curated and customized phages, serving as an efficient platform for phage study.

A recommender system (RS) relying on latent factor analysis usually adopts stochastic gradient descent (SGD) as its learning algorithm. However, owing to its serial mechanism, an SGD algorithm suffers from low efficiency and scalability when handling large-scale industrial problems. Aiming at addressing this issue, this study proposes a momentum-incorporated parallel stochastic gradient descent (MPSGD) algorithm, whose main idea is two-fold: a) implementing parallelization via a novel data-splitting strategy, and b) accelerating convergence rate by integrating momentum effects into its training process. With it, an MPSGD-based latent factor (MLF) model is achieved, which is capable of performing efficient and high-quality recommendations. Experimental results on four high-dimensional and sparse matrices generated by industrial RS indicate that owing to an MPSGD algorithm, an MLF model outperforms the existing state-of-the-art ones in both computational efficiency and scalability.

Abstract Owing to their exceptional properties, high‐entropy alloys (HEAs) and high‐entropy materials have emerged as promising research areas and shown diverse applications. Here, the recent advances in the field are comprehensively reviewed, organized into five sections. The first section introduces the background of HEAs, covering their definition, significance, application prospects, basic properties, design principles, and microstructure. The subsequent section focuses on cutting‐edge high‐entropy structural materials, highlighting developments such as nanostructured alloys, grain boundary engineering, eutectic systems, cryogenic alloys, thin films, micro‐nano‐lattice structures, additive manufacturing, high entropy metallic glasses, nano‐precipitate strengthened alloys, composition modulation, alloy fibers, and refractory systems. In the following section, the emphasis shifts to functional materials, exploring HEAs as catalysts, magneto‐caloric materials, corrosion‐resistant alloys, radiation‐resistant alloys, hydrogen storage systems, and materials for biomedicine. Additionally, the review encompasses functional high‐entropy materials outside the realm of alloys, including thermoelectric, quantum dots, nanooxide catalysts, energy storage materials, negative thermal expansion ceramics, and high‐entropy wave absorption materials. The paper concludes with an outlook, discussing future directions and potential growth areas in the field. Through this comprehensive review, researchers, engineers, and scientists may gain valuable insights into the recent progress and opportunities for further exploration in the exciting domains of high‐entropy alloys and functional materials.

Coronary heart disease (CHD) is a dangerous condition that cannot be completely cured. Accurate detection of early coronary artery disease can assist physicians in treating patients. In this study, a prediction model called HY_OptGBM was proposed for predicting CHD by using the optimized LightGBM classifier. To optimize the LightGBM classifier, the hyperparameters of the LightGBM model were adjusted. In addition, its loss function was improved, and the model was trained using adjusted hyperparameters. In this study, the hyperparameters of the prediction model were optimized by applying the most advanced hyperparameter optimization framework (OPTUNA). The improved loss function is referred to as the focal loss (FL). In this study, a prediction model was evaluated by using CHD data from the Framingham Heart Institute. To evaluate the performance of the prediction model, various metrics, including precision, recall, F score, accuracy, MCC, sensitivity, specificity, and AUC, were used. The AUC value of the proposed model was 97.9%, which was better than that of other comparative models. The results demonstrate that the rate of early identification of CHD among the general population can be improved by utilizing the proposed method. This, in turn, could serve to mitigate the costs associated with the medical treatment of patients suffering from CHD.

Abstract Integrated electro-optic (EO) frequency combs are essential components for future applications in optical communications, light detection and ranging, optical computation, sensing and spectroscopy. To date, broadband on-chip EO combs are typically generated in high-quality-factor micro-resonators, while the more straightforward and flexible non-resonant method, usually using single or cascaded EO phase modulators, often requires high driving power to realize a reasonably strong modulation index. Here, we show that the phase modulation efficiency of an integrated lithium niobate modulator could be enhanced by passing optical signals through the modulation electrodes for a total of 4 round trips, via multiple low-loss mode multiplexers and a waveguide crossing, reducing electrical power consumption by an experimentally measured factor of 15. Using devices fabricated from a wafer-scale stepper lithography process, we demonstrate a broadband optical frequency comb featuring 47 comb lines at a 25-GHz repetition rate, using a moderate radio frequency (RF) driving power of 28 dBm (0.63 W). Leveraging the tunability in repetition rate and operation wavelength, our power-efficient EO comb generator could serve as a compact low-cost solution for future high-speed data transmission, sensing and spectroscopy, as well as classical and quantum optical computation systems.

Abstract Surface wear is a major hindrance in the solid/solid interface of triboelectric nanogenerators (TENG), severely affecting their output performance and stability. To reduce the mechanical input and surface wear, solid/liquid-interface alternatives have been investigated; however, charge generation capability is still lower than that in previously reported solid/solid-interface TENGs. Thus, achieving triboelectric interface with high surface charge generation capability and low surface wear remains a technological challenge. Here, we employ metallic glass as one triboelectric interface and show it can enhance the triboelectrification efficiency by up to 339.2%, with improved output performance. Through mechanical and electrical characterizations, we show that metallic glass presents a lower friction coefficient and better wear resistance, as compared with copper. Attributed to their low atomic density and the absence of grain boundaries, all samples show a higher triboelectrification efficiency than copper. Additionally, the devices demonstrate excellent humidity resistance. Under different gas pressures, we also show that metallic glass-based triboelectric nanogenerators can approach the theoretical limit of charge generation, exceeding that of Cu-based TENG by 35.2%. A peak power density of 15 MW·m -2 is achieved. In short, this work demonstrates a humidity- and wear-resistant metallic glass-based TENG with high triboelectrification efficiency.

With the emergence of big data, cloud computing, and other technologies, artificial intelligence (AI) technology has set off a new wave in the field of education. The application of AI technology to deep learning in university teachers' teaching and students' learning processes is an innovative way to promote the quality of teaching and learning. This study proposed the deep learning-based assessment to measure whether students experienced an improvement in terms of their mastery of knowledge, development of abilities, and emotional experiences. It also used comparative analysis of pre-tests and post-tests through online questionnaires to test the results. The impact of technology on teachers' teaching and students' learning processes, identified the problems in the teaching and learning processes in the context of the application of AI technology, and proposed strategies for reforming and optimizing teaching and learning. It recommends the application of software and platforms, such as Waston and Knewton, under the orientation of AI technology to improve efficiency in teaching and learning, optimize course design, and engage students in deep learning. The contribution of this research is that the teaching and learning processes will be enhanced by the use of intelligent and efficient teaching models on the teachers' side and personalized and in-depth learning on the students' side. On the one hand, the findings are helpful for teachers to better grasp the actual conditions of in-class teaching in real time, carry out intelligent lesson preparations, enrich teaching methods, improve teaching efficiency, and achieve personalized and precision teaching. On the other hand, it also provides a space of intelligent support for students with different traits in terms of learning and effectively improves students' innovation ability, ultimately achieving the purpose of "artificial intelligence + education."

A unique integrated hollow CoP nanospheres embedded carbon nanoarrays has been facilely synthesized from a metal–organic framework precursor, and behaves as a pH-versatile catalyst for both hydrogen evolution and oxygen evolution reactions.

OBJECTIVE: Deep learning (DL) techniques have been introduced to assist doctors in the interpretation of medical images by detecting image-derived phenotype abnormality. Yet the privacy-preserving policy of medical images disables the effective training of DL model using sufficiently large datasets. As a decentralized computing paradigm to address this issue, federated learning (FL) allows the training process to occur in individual institutions with local datasets, and then aggregates the resultant weights without risk of privacy leakage. METHODS: We propose an effective federated multi-task learning (MTL) framework to jointly identify multiple related mental disorders based on functional magnetic resonance imaging data. A federated contrastive learning-based feature extractor is developed to extract high-level features across client models. To ease the optimization conflicts of updating shared parameters in MTL, we present a federated multi-gate mixture of expert classifier for the joint classification. The proposed framework also provides practical modules, including personalized model learning, privacy protection, and federated biomarker interpretation. RESULTS: On real-world datasets, the proposed framework achieves robust diagnosis accuracies of 69.48 ± 1.6%, 71.44 ± 3.2%, and 83.29 ± 3.2% in autism spectrum disorder, attention deficit/hyperactivity disorder, and schizophrenia, respectively. CONCLUSION: The proposed framework can effectively ease the domain shift between clients via federated MTL. SIGNIFICANCE: The current work provides insights into exploiting the advantageous knowledge shared in related mental disorders for improving the generalization capability of computer-aided detection approaches.

The rapid growth of the Internet of Vehicles (IoV) paradigm sparks the generation of large volumes of distributed data at vehicles, which can be harnessed to build models for intelligent applications. Federated learning has recently received wide attentions, which allows model training over distributed datasets without requiring raw datasets to be shared out. However, federated learning is known to be vulnerable to poisoning attacks, where malicious clients may manipulate the local datasets or model updates to corrupt the global model. Such attacks have to be countered when federated learning is adopted in IoV systems, given that the training process is distributed among a large number of vehicles in an open environment. In addition, IoV systems present a hierarchical architecture in practice where other types of nodes sit between the cloud server and vehicles, allowing intermediate aggregation for reducing overall training latency. Yet the intermediate aggregation nodes may also pose threats. In this paper, we propose a robust hierarchical federated learning framework named RoHFL, which allows hierarchical federated learning to be suitably applied in the IoV with robustness against poisoning attacks. We develop a robust model aggregation scheme that contains a logarithm-based normalization mechanism to cope with scaled gradients from malicious vehicles. We integrate the notion of reputation into the aggregation process and develop a scheme for reputation updating. We provide a formal analysis of RoHFL’s convergence guarantees. Experiment results over several popular datasets demonstrate the promising performance of RoHFL, which is superior to prior work in the robustness against poisoning attacks.

Neuroimaging techniques have been widely adopted to detect the neurological brain structures and functions of the nervous system. As an effective noninvasive neuroimaging technique, functional magnetic resonance imaging (fMRI) has been extensively used in computer-aided diagnosis (CAD) of mental disorders, e.g., autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD). In this study, we propose a spatial-temporal co-attention learning (STCAL) model for diagnosing ASD and ADHD from fMRI data. In particular, a guided co-attention (GCA) module is developed to model the intermodal interactions of spatial and temporal signal patterns. A novel sliding cluster attention module is designed to address global feature dependency of self-attention mechanism in fMRI time series. Comprehensive experimental results demonstrate that our STCAL model can achieve competitive accuracies of 73.0 ± 4.5%, 72.0 ± 3.8%, and 72.5 ± 4.2% on the ABIDE I, ABIDE II, and ADHD-200 datasets, respectively. Moreover, the potential for feature pruning based on the co-attention scores is validated by the simulation experiment. The clinical interpretation analysis of STCAL can allow medical professionals to concentrate on the discriminative regions of interest and key time frames from fMRI data.

Mesenchymal stem cells (MSCs) interact with tumor cells and regulate tumorigenesis and metastasis. As one of the important components of the tumor microenvironment, MSC-secreted cytokines play a critical role in cancer development. However, whether and how bone marrow MSCs (BMSCs) and their secreted cytokines participate in hepatocellular carcinoma (HCC) progression, still remains largely unknown. In the present study, we first measured the concentration of interleukin-6 (IL-6) in BMSC conditioned medium (BMSC-CM). Next, we assessed the changes of invasion ability in response to treatment of BMSC-CM or recombinant IL-6 in two human HCC cell lines Bel-7404 and HepG2. Then we analyzed the level of key components of the IL-6 signal pathway, including IL-6 receptor and signal transducer (i.e. IL-6R and gp130), a transcription factor STAT3 (signal transducer and activator of transcription 3), as well as its target genes BCL2, CCND1, MCL1 and MMP2, in BMSC-CM or recombinant IL-6 treated Bel-7404 and HepG2 cells. Results showed that a considerable amount of IL-6 was secreted by BMSCs, and BMSC-CM markedly elevated Bel-7404 cell invasion rate and stimulated the signal transduction of IL-6/STAT3 pathway. Neutralizing the secreted IL-6 bioactivity by the anti-IL-6 antibody diminished the invasion-promoting effect and down-regulated IL-6/STAT3 pathway of BMSC-CM treated Bel-7404 cells. In conclusion, we found that BMSCs may activate the IL-6/STAT3 signaling pathway and promote cell invasion in Bel-7404 cells, suggesting that this protumor effect should be seriously considered before clinical application of MSC-mediated cancer therapy.

Abstract The design of bulk metallic glasses (BMGs) via machine learning (ML) has been a topic of active research recently. However, the prior ML models were mostly built upon supervised learning algorithms with human inputs to navigate the high dimensional compositional space, which becomes inefficient with the increasing compositional complexity in BMGs. Here, we develop a generative deep-learning framework to directly generate compositionally complex BMGs, such as high entropy BMGs. Our framework is built on the unsupervised Generative Adversarial Network (GAN) algorithm for data generation and the supervised Boosted Trees algorithm for data evaluation. We studied systematically the confounding effect of various data descriptors and the literature data on the effectiveness of our framework both numerically and experimentally. Most importantly, we demonstrate that our generative deep learning framework is capable of producing composition-property mappings, therefore paving the way for the inverse design of BMGs.

College English cross-cultural teaching has changed from offline to online teaching. Under the impetus of MOOC teaching mode, college English cross-cultural teaching online teaching has exposed problems such as insufficient intelligence and poor online teaching effects. In order to improve the efficiency of college English cross-cultural teaching, based on cloud computing technology and artificial intelligence technology, this article improves and analyzes traditional MOOC, improves traditional algorithms according to the actual needs of MOOC teaching, and proposes a new improved model. Moreover, this article sets up functional modules through requirements analysis. In addition, according to actual teaching, this paper designs control experiments to verify and analyze the model performance from experimental teaching and the effect of attracting students’ online learning. The research results show that the model proposed in this paper has good performance and can effectively improve the efficiency of English cross-cultural teaching.

NPs electrodes function as both anodes. The as-fabricated PEC-MFC hybrid device can simultaneously realize electricity and hydrogen using organic matter and solar light at zero external bias. This novel design and attempt might provide guidance for other materials to convert and store energy.

In order to investigate the changing patterns and influencing factors of ecosystem service values (ESV) provided by the “production-life-ecological space” (PLES) in the karst-Beibu Gulf of southwest Guangxi under the geographical characteristics of the mountain-river-sea transition zone, this study selected land use data at four time points from 1990 to 2020, clarified the characteristics of regional ESV evolution through spatial autocorrelation analysis and standard deviation ellipse, and explored its formation mechanism with the help of geographic probes. The results showed that: (1) The overall spatial variation of the total ESV in the study area was obvious, with “high in the southwest and low in the northeast” and a decreasing trend in general. (2) The ESV in PLES perspective showed positive spatial autocorrelation overall and exhibited obvious spatial aggregation characteristics. Their center of gravity as a whole shifts to the southeast, the ellipse area keeps expanding, and the center of gravity positions all remain in Nanning City. (3) ESV evolution is closely related to natural, economic, and social factors, with rocky desertification area and Normalized Difference Vegetation Index (NDVI) having the most significant spatial differentiation effect on ESV provided by production space and ecological space, average altitude contributing more to ESV provided by living space, and interaction between various elements improving ESV differentiation from the perspective of PLES. The results of the study provide a scientific basis for optimizing regional territorial spatial planning and improving regional ESV.

The globally rising prevalence of mental disorders leads to shortfalls in timely diagnosis and therapy to reduce patients' suffering. Facing such an urgent public health problem, professional efforts based on symptom criteria are seriously overstretched. Recently, the successful applications of computer-aided diagnosis approaches have provided timely opportunities to relieve the tension in healthcare services. Particularly, multimodal representation learning gains increasing attention thanks to the high temporal and spatial resolution information extracted from neuroimaging fusion. In this work, we propose an efficient multimodality fusion framework to identify multiple mental disorders based on the combination of functional and structural magnetic resonance imaging. A multioutput conditional generative adversarial network (GAN) is developed to address the scarcity of multimodal data for augmentation. Based on the augmented training data, the multiheaded gating fusion model is proposed for classification by extracting the complementary features across different modalities. The experiments demonstrate that the proposed model can achieve robust accuracies of 75.1 ± 1.5 %, 72.9 ± 1.1 %, and 87.2 ± 1.5 % for autism spectrum disorder (ASD), attention deficit/hyperactivity disorder, and schizophrenia, respectively. In addition, the interpretability of our model is expected to enable the identification of remarkable neuropathology diagnostic biomarkers, leading to well-informed therapeutic decisions.

Federated learning is a machine learning prgadigm that enables the collaborative learning among clients while keeping the privacy of clients’ data. Federated multitask learning (FMTL) deals with the statistic challenge of non-independent and identically distributed (IID) data by training a personalized model for each client, and yet requires all the clients to be always online in each training round. To eliminate the limitation of full-participation, we explore multitask learning associated with model clustering, and first propose a clustered FMTL to achieve the multual-task learning on non-IID data, while simultaneously improving the communication efficiency and the model accuracy. To enhance its privacy, we adopt a general dual-server architecture and further propose a secure clustered FMTL by designing a series of secure two-party computation protocols. The convergence analysis and security analysis is conducted to prove the correctness and security of our methods. Numeric evaluation on public data sets validates that our methods are superior to state-of-the-art methods in dealing with non-IID data while protecting the privacy.