Search

Abstract Anomaly detection on attributed graphs is a crucial topic for practical applications. Existing methods suffer from semantic mixture and imbalance issue because they commonly optimize the model based on the loss function for anomaly discrimination, mainly focusing on anomaly discrimination and ignoring representation learning. Graph Neural networks based techniques usually tend to map adjacent nodes into close semantic space. However, anomalous nodes commonly connect with numerous normal nodes directly, conflicting with the assortativity assumption. Additionally, there are far fewer anomalous nodes than normal nodes, leading to the imbalance problem. To address these challenges, a unique algorithm, decoupled self-supervised learning for anomaly detection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD.

Foundation models (e.g., ChatGPT, DALL-E, PengCheng Mind, PanGu-$\Sigma$) have demonstrated extraordinary performance in key technological areas, such as natural language processing and visual recognition, and have become the mainstream trend of artificial general intelligence. This has led more and more major technology giants to dedicate significant human and financial resources to actively develop their foundation model systems, which drives continuous growth of these models' parameters. As a result, the training and serving of these models have posed significant challenges, including substantial computing power, memory consumption, bandwidth demands, etc. Therefore, employing efficient training and serving strategies becomes particularly crucial. Many researchers have actively explored and proposed effective methods. So, a comprehensive survey of them is essential for system developers and researchers. This paper extensively explores the methods employed in training and serving foundation models from various perspectives. It provides a detailed categorization of these state-of-the-art methods, including finer aspects such as network, computing, and storage. Additionally, the paper summarizes the challenges and presents a perspective on the future development direction of foundation model systems. Through comprehensive discussion and analysis, it hopes to provide a solid theoretical basis and practical guidance for future research and applications, promoting continuous innovation and development in foundation model systems.

Federated Learning (FL), as a promising distributed learning paradigm, is proposed to solve the contradiction between the data hunger of modern machine learning and the increasingly stringent need for data privacy. However, clients naturally present different distributions of their local data and inconsistent local optima, which leads to poor model performance of FL. Many previous methods focus on mitigating objective inconsistency. Although local objective consistency can be guaranteed when the number of communication rounds is infinite, we should notice that the accumulation of global drift and the limitation on the potential of local updates are non-negligible in those previous methods. In this article, we study a new framework for data-heterogeneity FL, in which the local updates in clients towards the global optimum can accelerate FL. We propose a new approach called Slingshot. Slingshot's design goals are twofold, i.e., i) to retain the potential of local updates, and ii) to combine local and global trends. Experimental results show that Slingshot helps local updates become more globally favorable and outperforms other popular methods under various FL settings. For example, on CIFAR10, Slingshot achieves 46.52% improvement in test accuracy and 48.21× speedup for a lightweight neural network named SqueezeNet.

Web3, the next generation of the Internet, represents a decentralized and democratized web. Although it has garnered significant public interest and found numerous real-world applications, there is a limited understanding of people's perceptions and experiences with Web3. In this study, we conducted an empirical study to investigate the categories of Web3 applications and their popularity, as well as the potential challenges and opportunities within this emerging landscape. Our research was carried out in two phases. In the first phase, we analyzed 200 popular Web3 projects associated with 10 leading Web3 venture capital firms. In the second phase, we collected and examined code-related data from GitHub and market-related data from blockchain browsers (e.g., Etherscan) for these projects. Our analysis revealed that the Web3 ecosystem can be categorized into two groups, i.e., Web3 infrastructure and Web3 applications, with each consisting of several subcategories or subdomains. We also gained insights into the popularity of these Web3 projects at both the code and market levels and pointed out the challenges in the Web3 ecosystem at the system, developer, and user levels, as well as the opportunities it presents. Our findings contribute to a better understanding of Web3 for researchers and developers, which in turn promotes further exploration and advancement in this innovative field.

Objective The objective of this study was to investigate the phylogenetic and expression analysis of the angiopoietin-like (ANGPTL) gene family and their role in lipid metabolism in pigs. Methods In this study, the amino acid sequence analysis, phylogenetic analysis, and chromosome adjacent gene analysis were performed to identify the ANGPTL gene family in pigs. According to the body weight data from 60 Jinhua pigs, different tissues of 6 pigs with average body weight were used to determine the expression profile of ANGPTL1–8. The ileum, subcutaneous fat, and liver of 8 pigs with distinct fatness were selected to analyze the gene expression of ANGPTL3, ANGPTL4, and ANGPTL8. Results The sequence length of ANGPTLs in pigs was between 1,186 and 1,991 bp, and the pig ANGPTL family members shared common features with human homologous genes, including the high similarity of the amino acid sequence and chromosome flanking genes. Amino acid sequence analysis showed that ANGPTL1–7 had a highly conserved domain except for ANGPTL8. Phylogenetic analysis showed that each ANGPTL homologous gene shared a common origin. Quantitative reverse-transcription polymerase chain reaction analysis showed that ANGPTL family members had different expression patterns in different tissues. ANGPTL3 and ANGPTL8 were mainly expressed in the liver, while ANGPTL4 was expressed in many other tissues, such as the intestine and subcutaneous fat. The expression levels of ANGPTL3 in the liver and ANGPTL4 in the liver, intestine and subcutaneous fat of Jinhua pigs with low propensity for adipogenesis were significantly higher than those of high propensity for adipogenesis. Conclusion These results increase our knowledge about the biological role of the ANGPTL family in this important economic species, it will also help to better understand the role of ANGPTL3, ANGPTL4, and ANGPTL8 in lipid metabolism of pigs, and provide innovative ideas for developing strategies to improve meat quality of pigs.

Abstract Blockchain and blockchain‐based decentralised applications have been attracting increasing attention recently. In public blockchain systems, users usually connect to third‐party peers or run a peer to join the P2P blockchain network. However, connecting to unreliable blockchain peers will lead to resource waste and even loss of cryptocurrencies by repeated transactions. In order to select reliable blockchain peers, it is urgently needed to evaluate and predict their reliability of them. Faced with this problem, we propose hybrid blockchain reliability prediction (H‐BRP), a Hybrid Blockchain Reliability Prediction model, to extract the blockchain reliability factors and then make the personalised prediction for each user. Comprehensive experiments conducted on 100 blockchain requesters and 200 blockchain peers demonstrate the effectiveness of the proposed H‐BRP model. Further, the implementation and dataset of 2,000,000 test cases are released.

With the development of the blockchain technology, a decentralized and de-trusted network paradigm has been constructed, enabling multiple digital assets like NFT, to be permanently recorded and authenticated by blockchain. Also, the uniqueness and verifiability of these assets allows them to flow and generate value between any network entities. With the emergence of AI Generative Content (AIGC), the ownership of models and generative contents, which are also digital assets, has not been well protected. Both because the black-box nature of neural networks makes it difficult to mark models' ownership and because the lack of a reliable third-party verification platform. Meanwhile, the existing model-attack threat and raising ethical problems driven the research on model watermark embedding for traceability and verification, and thus the reliable basic algorithm and the verification platform are needed. In this survey, while emphasizing the importance and reason of the ownership protection in AIGC and summarizing the recent research using model watermarking, we will also introduce the achievements of blockchain in copyright in order to summarize the research history and point out future direction of model copyright validation from both the underlying technology and the supporting platform.

Blockchain-based decentralized applications (DApp) draw more attention with the increasing development and wide application of blockchain technologies. A wealth of funds are invested into the crowd-funding of various types of DApp. As reported in August 2022, there are more than 5,000 DApps with more than 1.67 million daily Unique Active Wallets (users). However, the definition, architectures, and classifications of the DApps are still not cleared up till now. This survey aims to provide a comprehensive overview of DApps for further research. First, the definitions and typical architectures of DApps are presented. Then we collect 3,118 popular DApps and categorize them into different types, and summarize their typical advantages and challenges. Finally, we provide an overview of the recent research problems of DApps from the perspectives of economics, security, and performance and then figure out promising research opportunities in the future.

At present, the concept of metaverse has sparked widespread attention from the public to major industries. With the rapid development of blockchain and Web3 technologies, the decentralized metaverse ecology has attracted a large influx of users and capital. Due to the lack of industry standards and regulatory rules, the Web3-empowered metaverse ecosystem has witnessed a variety of financial crimes, such as scams, code exploit, wash trading, money laundering, and illegal services and shops. To this end, it is especially urgent and critical to summarize and classify the financial security threats on the Web3-empowered metaverse in order to maintain the long-term healthy development of its ecology. In this paper, we first outline the background, foundation, and applications of the Web3 metaverse. Then, we provide a comprehensive overview and taxonomy of the security risks and financial crimes that have emerged since the development of the decentralized metaverse. For each financial crime, we focus on three issues: a) existing definitions, b) relevant cases and analysis, and c) existing academic research on this type of crime. Next, from the perspective of academic research and government policy, we summarize the current anti-crime measurements and technologies in the metaverse. Finally, we discuss the opportunities and challenges in behavioral mining and the potential regulation of financial activities in the metaverse. The overview of this paper is expected to help readers better understand the potential security threats in this emerging ecology, and to provide insights and references for financial crime fighting.

Smart contract has been the core of blockchain systems and other blockchain-based systems since Blockchain 2.0. Various operations on blockchain are performed through the invocation and execution of smart contracts. This leads to extensive combinations between blockchain, smart contract, Internet of Things (IoT) and Cyber-Physical System (CPS) applications, and then many blockchain-based IoT or CPS applications emerge to provide multiple benefits to the economy and society. In this case, obtaining a better understanding of smart contracts will contribute to the easier operation, higher efficiency and stronger security of those blockchain-based systems and applications. Many existing studies on smart contract analysis are based on similarity calculation and smart contract classification. However, smart contract is a piece of code with special characteristics and most of smart contracts are stored without any category labels, which leads to difficulties of smart contract classification. As the back end of a blockchain-based Decentralized Application (DApp) is one or several smart contracts, DApps with labeled categories and open source codes are applied to achieve a supervised smart contract classification. A three-phase approach is proposed to categorize DApps based on various data features. In this approach, 5,659 DApps with smart contract source codes and pre-tagged categories are first obtained based on massive collected DApps and smart contracts from Ethereum, State of the DApps and DappRadar. Then feature extraction and construction methods are designed to form multi-feature vectors that could present the major characteristics of DApps. Finally, a fused classification model consisting of KNN, XGBoost and random forests is applied to the multi-feature vectors of all DApps for performing DApp classification. The experimental results show that the method is effective. In addition, some positive correlations between feature variables and categories, as well as several user behavior patterns of DApp calls, are found in this paper.

Abstract β-1,3/1,6-glucan as a prebiotic improves immune performance in animals. These functions are closely related to the effect of β-1,3/1,6-glucan on gut microbiota structure. However, the effect of β-1,3/1,6-glucan on the gut microbiota structure of broilers is unclear. The aim of this study was to confirm the effects of β-1,3/1,6-glucan on the cecal microflora structure of yellow-feathered broilers. This study monitored the antimicrobial resistance (AMR) level of Escherichia coli in feces of yellow-feathered broilers by standard broth dilution method and mastered the AMR level of chickens selected. The effects of β-1,3/1,6-glucan on gut microbiota were investigated by 16S rRNA sequencing. The results showed that the number of isolated multidrug-resistant E. coli strains accounted for 98.41%. At 14, 21, and 28 days of age, supplemented of 0.2%, 0.1%, and 0.1% β-1,3/1,6-glucan in yellow-feathered broiler diets significantly altered gut microbial composition, and beneficial bacteria Alistipes, Bacteroides and Faecalibacterium were significantly increased. These findings provide guidance and recommendations for β-1,3/1,6-glucan as a broiler feed additive to improve the growth of broilers.

With the continuous development of web technology, Web3.0 has attracted a considerable amount of attention due to its unique decentralized characteristics. The digital economy is an important driver of high-quality economic development and is currently in a rapid development stage. In the digital economy scenario, the centralized nature of the Internet and other characteristics usually bring about security issues such as infringement and privacy leakage. Therefore, it is necessary to investigate how to use Web3.0 technologies to solve the pain points encountered in the development of the digital economy by fully exploring the critical technologies of digital economy and Web3.0. In this paper, we discuss the aspects of Web3.0 that should be integrated with the digital economy to better find the entry point to solve the problems by examining the latest advances of Web3.0 in machine learning, finance, and data management. We hope this research will inspire those who are involved in both academia and industry, and finally help to build a favourable ecology for the digital economy.

Metaverse as the latest buzzword has attracted great attention from both industry and academia. Metaverse seamlessly integrates the real world with the virtual world and allows avatars to carry out rich activities including creation, display, entertainment, social networking, and trading. Thus, it is promising to build an exciting digital world and to transform a better physical world through the exploration of the metaverse. In this survey, we dive into the metaverse by discussing how Blockchain and Artificial Intelligence (AI) fuse with it through investigating the state-of-the-art studies across the metaverse components, digital currencies, AI applications in the virtual world, and blockchain-empowered technologies. Further exploitation and interdisciplinary research on the fusion of AI and Blockchain towards metaverse will definitely require collaboration from both academia and industries. We wish that our survey can help researchers, engineers, and educators build an open, fair, and rational future metaverse.

High fructose corn syrup (HFCS) is a viscous mixture of glucose and fructose that is used primarily as a food additive. This article explored the effect of HFCS on lipid metabolism-expressed genes and the mouse gut microbiome. In total, ten 3-week-old male C57BL/6J mice were randomly divided into two groups, including the control group, given purified water (Group C) and 30% HFCS in water (Group H) for 16 weeks. Liver and colonic content were collected for transcriptome sequencing and 16S rRNA gene sequencing, respectively. HFCS significantly increased body weight, epididymal, perirenal fat weight in mice (p < 0.05), and the proportion of lipid droplets in liver tissue. The expression of the ELOVL fatty acid elongase 3 (Elovl3) gene was reduced, while Stearoyl-Coenzyme A desaturase 1 (Scd1), peroxisome proliferator activated receptor gamma (Pparg), fatty acid desaturase 2 (Fads2), acyl-CoA thioesterase 2 (Acot2), acyl-CoA thioesterase 2 (Acot3), acyl-CoA thioesterase 4 (Acot4), and fatty acid binding protein 2 (Fabp2) was increased in Group H. Compared with Group C, the abundance of Firmicutes was decreased in Group H, while the abundance of Bacteroidetes was increased, and the ratio of Firmicutes/Bacteroidetes was obviously decreased. At the genus level, the relative abundance of Bifidobacterium, Lactobacillus, Faecalibaculum, Erysipelatoclostridium, and Parasutterella was increased in Group H, whereas that of Staphylococcus, Peptococcus, Parabacteroides, Donghicola, and Turicibacter was reduced in Group H. Pparg, Acot2, Acot3, and Scd1 were positively correlated with Erysipelatoclostridium and negatively correlated with Parabacteroides, Staphylococcus, and Turicibacter. Bifidobacterium was negatively correlated with Elovl3. Overall, HFCS affects body lipid metabolism by affecting the expression of lipid metabolism genes in the liver through the gut microbiome.

We are enjoying the benefits brought by the accelerated development of computing systems and the Internet. However, we are also facing a few security and privacy vulnerabilities caused by the increasing system complexity, heterogeneity, dynamicity, and decentralized nature. These security and privacy vulnerabilities may prevent the wide adoption of information and communications technology (ICT). Therefore, trust management has become a crucial aspect of developing trustworthy systems with the preservation of security and privacy. The recent advances in blockchain technologies are bringing opportunities in fully realizing trustworthy systems. Blockchain technologies can enable anonymous and trustful transactions in decentralized and trustless environments. As a result, blockchain-enabled trust management must help to reduce system risks, mitigate financial fraud, and cut down the operational cost of computing systems. Blockchain-enabled trustworthy systems can apply to diverse areas, such as financial services, social management, the Internet of Things, and supply chain management.

Decentralized Autonomous Organization (DAO) is believed to play a significant role in our future society governed in a decentralized way. In this article, we first explain the definitions and preliminaries of DAO. Then, we conduct a literature review of the existing studies of DAO published in the recent few years. Through the literature review, we find out that a comprehensive survey towards the state-of-the-art studies of DAO is still missing. To fill this gap, we perform such an overview by identifying and classifying the most valuable proposals and perspectives closely related to the combination of DAO and blockchain technologies. We anticipate that this survey can help researchers, engineers, and educators acknowledge the cutting-edge development of blockchain-related DAO technologies.

Sucralose is a non-nutritive artificial sweetener (NNS) used in foods or beverages to control blood glucose levels and body weight gain. The consumption of NNS has increased in recent years over the world, and many researches have indicated long-term sucralose administration altered the gut microbiome composition of mice. These studies all focus on the US Food and Drug Administration (FDA) defined acceptable daily intake (ADI), approximately 5 mg/kg BW/day for human. In our study, mice were given with T1-4 (0.0003, 0.003, 0.03, and 0.3 mg/mL) of sucralose, respectively, Control group mice were given normal water. In particular, 0.3 mg/mL of sucralose was equal to the ADI (5 mg/kg BW/day). After 16 weeks, all mice were weighted and sacrificed, the liver of each mouse was isolated and weighed, segments of jejunum, ileum and colon were collected for H&E-stained. The contents of jejunum, ileum, cecum and colon were collected for 16S rRNA gene sequencing. The results showed sucralose administration affects the intestinal barrier function evidenced by distinct lymphocyte aggregation in ileum and colon while not change the mice body weight. The 16S rRNA gene sequencing of the mice gut microbiome suggested sucralose administration significantly changed the composition of gut microbiota, especially in T1 and T4 group. For example, a reduction of probiotics abundance (Lachnoclostridium and Lachnospiraceae) was found in cecum of T4 group mice compared with Control group. On the other hand, Allobaculum, which was reported positively correlated with diabetes, was increased in the T1 and T4 group. In addition, the potential pathogens, including Tenacibaculum, Ruegeria, Staphylococcus were also increased in jejunum, ileum and colon by sucralose administration in T1 and T4 group. These new findings indicate that low dose of sucralose (T1) alter gut microbiome in mice, and these adverse health effects are equal to ADI level (T4). Overall, our study provides guidance and suggestions for the use of sucralose in foods and beverages.

Blockchain-based cryptocurrencies have received extensive attention recently. Massive data has been stored on permission-less blockchains. The analysis of massive blockchain data can bring huge business values. However, the absence of well-processed up-to-date blockchain datasets impedes big data analytics of blockchain data. To fill this gap, we collect and process the up-to-date on-chain data from Ethereum, which is one of the most popular permission-less blockchains. We name such well-processed Ethereum data as XBlock-ETH, which consists of transactions, smart contracts, and cryptocurrencies (i.e., tokens). However, it is non-trivial to partition and categorize the collected raw Ethereum data to the well-processed datasets since the whole processing procedure requires sophisticated knowledge on software engineering as well as big data analytics. Moreover, we also present basic statistics and exploration for each of the well-processed datasets. Furthermore, we also outline the possible research opportunities based on XBlock-ETH, with the data and code released online.

Constructing globally distributed file systems (DFS) has received great attention. Traditional Peer-to-Peer (P2P) distributed file systems have inevitable drawbacks such as instability, lacking auditing and incentive mechanisms. Thus, Inter-Planetary File System (IPFS) and Swarm, as the representative DFSs which integrate with blockchain technologies, are proposed and becoming a new generation of distributed file systems. Although the blockchain-based DFSs successfully provide adequate incentives and security guarantees by exploiting the advantages of blockchain, a series of challenges, such as scalability and privacy issues, are also constraining the development of the new generation of DFSs. Mainly focusing on IPFS and Swarm, this paper conducts an overview of the rationale, layered structure and cutting-edge studies of the blockchain-based DFSs. Furthermore, we also identify their challenges, open issues and future directions. We anticipate that this survey can shed new light on the subsequent studies related to blockchain-based distributed file systems.

Over the past decade, a large number of software defect prediction approaches have been proposed to identify the defect-prone modules by mining software repositories. Recently, a novel scenario called Cross-Version Defect Prediction (CVDP) begins to draw increasing research interests, as it is more reasonable and applicable in practice to adopt the labeled defect data of previous versions to predict defects in the current version of the same project. As a software project often has multiple previous versions, CVDP on this kind of projects will face the following two critical but seldom reported issues, namely, data distribution difference and class overlapping. In this paper, we address these two issues by solving a version selection problem via a Cross-version model with Data Selection (CDS). The proposed CDS is a novel framework which treats the defect prediction of existing and new files in different ways. For the existing files, we propose a novel Clustering-based Multi-Version Classifier (CMVC), which can automatically select the training data from the most relevant and noise-free versions by assigning them higher weights than the others. We proposed a Weighted Sampling Model (WSM) for the new files which have never appeared in previous version by incorporating the outputs of CMVC. We evaluate the proposed CDS model on 28 versions across 8 software projects, and the experimental results demonstrate that CDS outperforms three baseline methods and a state-of-the-art approach in terms of three prevalent performance indicators.

Search engines are nowadays widely applied to store and analyze logs generated by large-scale distributed systems. To adapt to various workload scenarios, log search engines such as Elasticsearch usually expose a large number of performance-related configuration parameters. As manual configuring is time consuming and labor intensive, automatically tuning configuration parameters to optimize performance has been an urgent need. However, it is challenging because: 1) Due to the complex implementation, the relationship between performance and configuration parameters is difficult to model and thus the objective function is actually a black box; 2) In addition to application parameters, JVM and kernel parameters are also closely related to the performance and together they construct a high dimensional configuration space; 3) To iteratively search for the best configuration, a tool is necessary to automatically deploy the newly generated configuration and launch tests to measure the corresponding performance. To address these challenges, this paper designs and implements HDConfigor, an automatic holistic configuration parameter tuning tool for log search engines. In order to solve the high dimensional optimization problem, we propose a modified Random EMbedding Bayesian Optimization algorithm (mREMBO) in HDConfigor which is a black-box approach. Instead of directly using a black-box optimization algorithm such as Bayesian optimization (BO), mREMBO first generates a lower dimensional embedded space through introducing a random embedding matrix and then performs BO in this embedded space. Therefore, HDConfigor is able to find a competitive configuration automatically and quickly. We evaluate HDConfigor in an Elasticsearch cluster with different workload scenarios. Experimental results show that compared with the default configuration, the best relative median indexing results achieved by mREMBO can reach $2.07\times $ . In addition, under the same number of trials, mREMBO is able to find a configuration with at least a further 10.31% improvement in throughput compared to Random search, Simulated Annealing and BO.

The Solid (Social Linked Data) project focuses on data sharing and privacy security and aims to build a decentralized ecosystem that radically changes the way web applications work today. Our goal is to introduce a “trust access authentication system” to achieve secure authentication and fine-grained access control, thereby promoting the implementation of Solid. Blockchain, equipped with multiple security properties and authentication functions, is a crucial technology. In this paper, we present a blockchain-assisted system for secure authentication in Solid and for implementation of fine-grained access control policies. Specifically, we explore to integrate threshold RSA signatures in a permissioned blockchain system to enable a fault-tolerant distributed signature scheme, thereby enhancing the resilience and robustness of authentication system. Moreover, we utilize smart contract to control transaction flows and manage access control policies automatically. Experimental results show that our proposed trust access authentication system enhances security, scales well, and is efficient and economically feasible.

Blockchain-based decentralized cryptocurrencies have drawn much attention and been widely-deployed in recent years. Bitcoin, the first application of blockchain, achieves great success and promotes more development in this field. However, Bitcoin encounters performance problems of low throughput and high transaction latency. Other cryptocurrencies based on proof-of-work also inherit the flaws, leading to more concerns about the scalability of blockchain. This paper attempts to cover the existing scaling solutions for blockchain and classify them by level. In addition, we make comparisons between different methods and list some potential directions for solving the scalability problem of blockchain.

Friend recommendations based on social relationships have attracted thousands of research under the rapid development of social networks. However, most of the existing friend recommendation methods use user attributes or a single social network, while rarely integrating multiple social relationships to enhance the representation. This paper focuses on integrating various social relationships to guide the representation learning, and further generating personalized friend recommendations. We design an end-to-end framework based on multiple social networks to learn the potential features of users and construct a friend recommendation model named Multi-Social Graph Convolutional Network (MSGCN). It learns the features of higher-order neighbors from multiple social networks to enrich the representation of the target user based on the improved graph convolution neural network. In particular, some graph fusion strategies by adjusting and fusing the Laplace matrix of the graph are designed to integrate social relationships. Finally, we use Bayesian theory to transform friend recommendation into a sorting problem for personalized recommendation. The experimental results show that the proposed model outperforms the state-of-the-art methods.

The objective of this study was to investigate the rumen degradation characteristics of grain amaranth hay (Amaranthus hypochondriacus) at four different growth stages. The aim of this study was to evaluate the nutritional value of grain amaranth hay at different growth stages by chemical composition, in vivo digestibility, and in situ degradability. Three Boer goats with permanent ruminal fistulas were selected in this study. Amaranthus hay at four different growth stages (squaring stage (SS), initial bloom stage (IS), full-bloom stage (FS) and mature stage (MS)) was crushed and placed into nylon bags. Each sample was set up with three replicates, and two parallel samples were set up in fistulas at each time point. The rumen degradation rates of dry matter (DM), crude protein (CP), neutral detergent fibre (NDF) and acid detergent fibre (ADF) were determined at 0, 6, 12, 24, 36, 48 and 72 h. The results were as follows: (1) The concentration of CP in SS was the highest and was significantly higher than that in other stages (p < 0.05), whereas the contents of NDF and ADF gradually increased with the extension of the growing period and reached a maximum in MS; (2)The degradation of CP in the rumen at 72 h of SS and IS was more than 80%. Compared with other stages, the effective degradability of CP was highest in SS (p < 0.05) and reached 87.05% at 72 h, and the degradation rate was the lowest in MS; and (3) The effective degradability of NDF in IS was the highest (p < 0.05) and reached 69.326% at 72 h. The effective degradability of ADF in MS was the highest (p < 0.05) and reached 65.728% at 72 h. The effective degradability of DM and CP in SS was the highest. In conclusion, among the four stages, IS was superior in chemical composition and rumen degradability characteristics.

Increasing studies have shown that obesity is the primary cause of cardiovascular diseases, non-alcoholic fatty liver diseases, type 2 diabetes, and a variety of cancers. The dysfunction of gut microbiota was proved to result in obesity. Recent research indicated ANGPTL4 was a key regulator in lipid metabolism and a circulating medium for gut microbiota and fat deposition. The present study was conducted to investigate the alteration of gut microbiota and ANGPTL4 expression in the gastrointestinal tract of mice treated by the high-fat diet. Ten C57BL/6J mice were randomly allocated to two groups and fed with a high-fat diet (HFD) containing 60% fat or a normal-fat diet (Control) containing 10% fat. The segments of ileum and colon were collected for the determination of ANGPTL4 expression by RT-qPCR and immunohistochemical analysis while the ileal and colonic contents were collected for 16S rRNA gene sequencing. The results showed HFD significantly increased mice body weight, epididymal fat weight, perirenal fat weight, liver weight, and the lipid content in the liver (P < 0.05). The relative expression of ANGPTL4 and the ANGPTL4-positive cells in the ileum and colon of mice was significantly increased by HFD treatment. Furthermore, 16S rRNA gene sequencing of the ileal and colonic microbiota suggested that HFD treatment changed the composition of the gut microbiota. The ratio of Firmicutes to Bacteroidetes and the abundance of Allobaculum was significantly higher in the HFD group than in the Control group while the abundance of Adlercreutzia, Bifidobacterium, Prevotellaceae UCG-001, and Ruminococcus was significantly decreased. Interestingly, the abundance of Allobaculum was positively correlated with the expression of ANGPTL4. These findings provide a theoretical foundation for the development of strategies to control the obesity and related diseases by the regulation of ANGPTL4 and gut microbiota.

In the service network, there exist various objects and rich relations among them. These various objects and rich relations naturally form a heterogeneous information network. Service recommendations can help users to locate their desired services. Previous service recommendation studies mainly aim at homogeneous networks or consider few kinds of relations rather than using the rich heterogeneous information. In this paper, we propose a mashup group preference-based service recommendation method in the heterogeneous information network for mashup creation. First of all, we analyze the historical invocation records between mashups and services and exploit the heterogeneous information to construct diverse meta paths with different semantic meanings. Then, we measure the similarity between the starting object and the ending object from different perspectives and integrate different similarity measures to obtain the hybrid similarity. Next, we introduce group preference to capture the rich interactions among mashups and apply a group preference-based Bayesian personalized ranking algorithm to learn the model. Finally, we recommend a list of personalized ranking services for mashup developers. A series of experiments conducted on a real-world dataset demonstrate the superiority of our proposed approach over other baseline approaches.

With Android applications (apps) becoming increasingly popular, there exist huge risks lurking in the app marketplaces as most malicious software attempt to collect users' private information without their awareness. Although these apps request users' authorization for permissions, the users can still face privacy leakage issues due to their limited knowledge in distinguishing permissions. Thus, accurate and automatic permission checking is necessary and important for users' privacy protection. According to previous studies, analyzing app descriptions is a helpful way to examine whether some permissions are required for apps. Different from those studies, we consider app permissions from a more fine-grained perspective and aim at predicting the multiple correspondent permissions to one sentence of app description. In this paper, we propose an end-to-end framework for assessing the consistency between descriptions and permissions, named Assessing Consistency based on neural Network (AC-Net). For evaluation, a new dataset involving the description-to-permission correspondences of 1415 popular Android apps was built. The experiments demonstrate that AC-Net significantly outperforms the state-of-the-art method by over 24.5% in accurately predicting permissions from descriptions.

Blockchain, originated from Bitcoin system, has drawn intense attention from the academic community because of its decentralization, persistency, anonymity and auditability. In the past decade, the blockchain technology has evolved and became viable for various applications beyond the domain of finance. However, due to the complexity of blockchain technology, it is usually difficult and costly for most developers or teams to build, maintain and monitor a blockchain network that supports their applications. Most common developers or teams are unable to ensure the reliability and security of the blockchain system, which to a certain extent affects the quality of their applications. In this paper, we develop a BaaS platform called NutBaaS, which provides blockchain service over cloud computing environments, such as network deployment and system monitoring, smart contracts analysis and testing. Based on these services, developers can focus on the business code to explore how to apply blockchain technology more appropriately to their business scenarios, without bothering to maintain and monitor the system.

Blockchain technology becomes increasingly popular. It also attracts scams, for example, a Ponzi scheme, a classic fraud, has been found making a notable amount of money on Blockchain, which has a very negative impact. To help to deal with this issue and to provide reusable research data sets for future research, this paper collects real-world samples and proposes an approach to detect Ponzi schemes implemented as smart contracts (i.e., smart Ponzi schemes) on the blockchain. First, 200 smart Ponzi schemes are obtained by manually checking more than 3,000 open source smart contracts on the Ethereum platform. Then, two kinds of features are extracted from the transaction history and operation codes of the smart contracts. Finally, a classification model is presented to detect smart Ponzi schemes. The extensive experiments show that the proposed model performs better than many traditional classification models and can achieve high accuracy for practical use. By using the proposed approach, we estimate that there are more than 500 smart Ponzi schemes running on Ethereum. Based on these results, we propose to build a uniform platform to evaluate and monitor every created smart contract for early warning of scams.

In algorithmic trading, feature extraction and trading strategy design are two prominent challenges to acquire long-term profits. However, the previously proposed methods rely heavily on domain knowledge to extract handcrafted features and lack an effective way to dynamically adjust the trading strategy. With the recent breakthroughs of deep reinforcement learning (DRL), sequential real-world problems can be modeled and solved with a more human-like approach. In this paper, we propose a novel trading agent, based on deep reinforcement learning, to autonomously make trading decisions and gain profits in the dynamic financial markets. We extend the value-based deep Q-network (DQN) and the asynchronous advantage actor-critic (A3C) for better adapting to the trading market. Specifically, in order to automatically extract robust market representations and resolve the financial time series dependence, we utilize the stacked denoising autoencoders (SDAEs) and the long short-term memory (LSTM) as parts of the function approximator, respectively. Furthermore, we design several elaborate mechanisms to make the trading agent more practical to the real trading environment, such as position-controlled action and n-step reward. The experimental results show that our trading agent outperforms the baselines and achieves stable risk-adjusted returns in both the stock and the futures markets.

The aim of this study was to determine the effects of dietary supplementation with mannose oligosaccharide (MOS) on the condition of the body and the reproductive and lactation performances of sows. Eighty pregnant sows were randomly assigned to four groups with a 2 × 2 factorial design: with or without MOS (1 g/kg) and with or without heat stress (HS) challenge. The temperature in the HS groups (HS and HM group) was controlled at 31.56 ± 1.22 °C, while the temperature in the active cooling (AC) groups (AC and AM group) was controlled at 23.49 ± 0.72 °C. The weight loss of sows in the AC group was significantly lower than that of sows in the HS group (p < 0.01). The weight and backfat thickness loss of sows supplemented with MOS displayed a downward trend. The average birth weight of the litter significantly increased in the HM group (basic diet + MOS) compared with the HS group (p < 0.05). The milk protein of sows significantly decreased under the HS condition at 2 and 12 h after delivery (p < 0.05). However, the milk immunoglobin G (IgG) of sows in the HS group increased significantly compared with that of sows in the HM group (p < 0.05) at 12 and 24 h after delivery. The levels of serum urea nitrogen (UREA) and glucose (GLU) decreased significantly under the HS condition (p < 0.05), while the level of interleukin-6 (IL-6) increased significantly under the HS condition (p < 0.05). Dietary supplementation with MOS also significantly reduced TNF-α under the AC conditions (p < 0.05). In conclusion, HS significantly affected the body condition, lactation performances and their offspring of sows. However, dietary supplementation with 1 g/kg MOS did not result in statistically significant changes.

Recently, graph embedding techniques have been widely used in the analysis of various networks, but most of the existing embedding methods omit the network dynamics and the multiplicity of edges, so it is difficult to accurately describe the detailed characteristics of the transaction networks. Ethereum is a blockchain-based platform supporting smart contracts. The open nature of blockchain makes the transaction data on Ethereum completely public and also brings unprecedented opportunities for transaction network analysis. By taking the realistic rules and features of transaction networks into consideration, we first model the Ethereum transaction network as a Temporal Weighted Multidigraph (TWMDG) where each node is a unique Ethereum account and each edge represents a transaction weighted by amount and assigned a timestamp. We then define the problem of Temporal Weighted Multidigraph Embedding (T-EDGE) by incorporating both temporal and weighted information of the edges, the purpose being to capture more comprehensive properties of dynamic transaction networks. To evaluate the effectiveness of the proposed embedding method, we conduct experiments of node classification on real-world transaction data collected from Ethereum. Experimental results demonstrate that T-EDGE outperforms baseline embedding methods, indicating that time-dependent walks and the multiplicity characteristic of edges are informative and essential for time-sensitive transaction networks.

Identifying a small subset of influential individuals on social networks can bring great benefits for many practical applications like viral marketing. This issue is typically formulated as the influence maximization problem. As a fundamental research topic in social network analysis, influence maximization has attracted much attention in recent years. In general, traditional influence maximization algorithms can be classified into two categories: 1) greedy algorithms, which possess high-performance guarantee but are time-consuming and 2) heuristic algorithms, which are time-efficient but lack performance guarantee. In this paper, we first propose a community detection approach based on network embedding to detect the community structures of social networks. With the aid of these community structures, we then propose two novel and robust community-based approximation algorithms, basic community-based robust influence maximization (BCRIM) and improved community-based robust influence maximization (ICRIM), to combat the problem of influence maximization. Both BCRIM and ICRIM have high-performance guarantee as well as high efficiency, while ICRIM runs even faster than BCRIM. Specifically, BCRIM and ICRIM identify influential individuals within communities rather than the entire network. The influence scope of each individual in BCRIM and ICRIM is restricted to its community and its neighbors' communities; thus, they are able to simultaneously identify influential individuals within communities and important hub or bridge individuals that connect different communities together. Furthermore, we analyze the performance guarantee of BCRIM and ICRIM in detail. Finally, we conduct extensive experiments on five benchmark networks to evaluate the performance of the proposed algorithms.

Identifying influential nodes in complex networks is of great significance. During recent decades, numerous methods regarding influential nodes identification or important nodes ranking have been developed. However, most of the existing methods either have low ranking accuracy or cannot be extended to large-scale networks. To address these issues, we propose a novel greedy algorithm named backward generating networks (BGNs) to identify influential nodes more accurately and more efficiently. BGN seeks to get the order of importance of nodes by minimizing the unique robustness value, which is an effective and brand-new metric to evaluate the importance of each node locally or the entire ranking results globally. The unique robustness measurement is rooted in the well-known percolation theory that with a certain fraction of nodes in a network being removed, the network collapses as much as possible. That is, the giant connected component in the collapsed network gets as small as possible. Therefore, BGN aims at finding a node sequence such that the giant connected component reduces in the steepest way. To this end, instead of deleting nodes from the network forwardly, BGN chooses to reconstruct the network by gradually adding nodes to an empty network according to the requirement that the giant connected component grows as slow as possible. We further propose heap-BGN to speed up BGN, and initial-BGN to make BGN produce more accurate results by proper initial rankings. Extensive experiments on four real-world networks and four synthetic networks demonstrate that BGN can outperform the state-of-the-art baseline algorithms, in terms of both ranking accuracy and computational efficiency.

QoS (Quality of Service) (our approach can be applied to a wide variety of services; in this paper, we focus on Web services) performance is intensively relevant to locations due to the network distance and the Internet connection between users and services. Thus, considering the location information of services and users is necessary. However, the location information has been ignored by most previous work. In this paper, we take both services’ and users’ location information into account. Specifically, we propose a location-aware QoS prediction approach, called LANFM, by exploiting neural network techniques and factorization machine to improve user-perceived experience. First of all, the information (e.g., id and location) of services and users is expressed as embedding vectors by leveraging neural network techniques. Then, the inner product of various embedding vectors, along with the weighted sum of feature vectors, is used to predict the QoS values. It should be noted that the inner product operation could capture the interactions between services and users, which is helpful to predict QoS values of services that have not been invoked by users. A collection of extensive experiments have been carried out on a real-world dataset to validate the effectiveness of the LANFM model.

Bitcoin has attracted extensive attention from investors, researchers, regulators, and the media. A well-known and unusual feature is that Bitcoin’s price often fluctuates significantly, which has however received less attention. In this paper, we investigate the Bitcoin price fluctuation prediction problem, which can be described as whether Bitcoin price keeps or reversals after a large fluctuation. In this paper, three kinds of features are presented for the price fluctuation prediction, including basic features, traditional technical trading indicators, and features generated by a Denoising autoencoder. We evaluate these features using an Attentive LSTM network and an Embedding Network (ALEN). In particular, an attentive LSTM network can capture the time dependency representation of Bitcoin price and an embedding network can capture the hidden representations from related cryptocurrencies. Experimental results demonstrate that ALEN achieves superior state-of-the-art performance among all baselines. Furthermore, we investigate the impact of parameters on the Bitcoin price fluctuation prediction problem, which can be further used in a real trading environment by investors.