Both convergence and diversity are crucial to evolutionary many-objective optimization, whereas most existing dominance relations show poor performance in balancing them, thus easily leading to a set ...of solutions concentrating on a small region of the Pareto fronts. In this paper, a novel dominance relation is proposed to better balance convergence and diversity for evolutionary many-objective optimization. In the proposed dominance relation, an adaptive niching technique is developed based on the angles between the candidate solutions, where only the best converged candidate solution is identified to be nondominated in each niche. Experimental results demonstrate that the proposed dominance relation outperforms existing dominance relations in balancing convergence and diversity. A modified NSGA-II is suggested based on the proposed dominance relation, which shows competitiveness against the state-of-the-art algorithms in solving many-objective optimization problems. The effectiveness of the proposed dominance relation is also verified on several other existing multi- and many-objective evolutionary algorithms.
•We design a group-agent strategy with trust computing.•We propose a stacked task sorting and ranking mechanism.•We adopt a secure and efficient content model.•Simulation results show that our scheme ...has better computational efficiency and higher reliability.
In order to meet various needs of people, different Internet of Things (IoT) devices have been developed and applied successfully in recent years. However, the consequent challenges in terms of search efficiency, reliable requirements, and resource allocation appear followed, which attract attention from both academia and industry. Facing this circumstance, it is necessary to establish a new scheme to realize data processing and sharing better. Therefore, a reliable and efficient system based on edge computing and blockchain is proposed in this paper. First, a new group-agent strategy with trust computing is designed to ensure the reliability of edge devices during interactions and improve transmission efficiency. Second, we introduce a stacked task sorting and ranking mechanism which improves resource allocation in each edge device. Third, this paper creates a new content model that uses Zipf distribution to predict context popularity of keywords and encrypt hot data with symmetric searchable encryption (SSE) technology. Finally, simulation results show that the proposed scheme has better computational efficiency and higher reliability compared with existing methods.
Single cell RNA sequencing (scRNA-seq) enables researchers to characterize transcriptomic profiles at the single-cell resolution with increasingly high throughput. Clustering is a crucial step in ...single cell analysis. Clustering analysis of transcriptome profiled by scRNA-seq can reveal the heterogeneity and diversity of cells. However, single cell study still remains great challenges due to its high noise and dimension. Subspace clustering aims at discovering the intrinsic structure of data in unsupervised fashion. In this paper, we propose a deep sparse subspace clustering method scDSSC combining noise reduction and dimensionality reduction for scRNA-seq data, which simultaneously learns feature representation and clustering via explicit modelling of scRNA-seq data generation. Experiments on a variety of scRNA-seq datasets from thousands to tens of thousands of cells have shown that scDSSC can significantly improve clustering performance and facilitate the interpretability of clustering and downstream analysis. Compared to some popular scRNA-deq analysis methods, scDSSC outperformed state-of-the-art methods under various clustering performance metrics.
As one of the most popular evolutionary algorithms for solving complex optimization problems, genetic algorithm has been extensively studied in the last three decades. Since genetic algorithm is a ...stochastic algorithm that may revisit duplicated solutions, it could suffer from low convergence speed on some real-world problems making algorithms likely to get trapped into local optimums. To address this issue, this paper proposes a non-revisiting genetic algorithm with a novel binary space partition (BSP) tree. The proposed BSP tree records all the generated solutions, which enables the algorithm to quickly determine whether a newly generated solution is duplicated or not. Moreover, the proposed algorithm fine-tunes the solutions according to the topology of the BSP tree in each generation, and thus can improve the population diversity and convergence speed. In comparison to six representative evolutionary algorithms, the proposed non-revisiting genetic algorithm exhibits better overall performance on eight benchmark problems, the power system fault diagnosis problem, and the molecular signatures selection problem.
The traditional covert communication channel relying on a third-party node is vulnerable to attack. The data are easily tampered with and the identity information of the communication party is ...fragile. Blockchain has the characteristics of decentralization and tamper resistance, which can effectively solve the above problems. In addition, some confidential information needs to be transmitted covertly in the transparent blockchain. A smart contract deployed in the blockchain to automatically realize its function can replace a centralized node to provide credible guarantee for communication. The diversity of parameters, data redundancy, and code programmability of smart contract make it an excellent carrier for covert communication under blockchain. In this article, we propose a covert communication model combined with smart contracts to covertly transfer information in the blockchain environment. To implement this model, we use the parameters in the contract to map the secret information sequence, and call the contract to transfer message. Voting contract and secret bidding contract are combined to instantiate the proposed model, and optimized versions of the two contracts are also proposed to reduce costs. Moreover, we use encryption algorithms and two-round protocols to ensure data privacy and design corresponding information embedding and transmission methods for different scenarios. To improve the concealment of communication, redundant options, effective price ranges, and invalid bids are set in two contracts, respectively. The experimental results show that the proposed model has tamper resistance and low complexity, and it is feasible to use this model for covert communication.
Designing multiobjective evolutionary algorithms (MOEAs) for community detection in complex networks has attracted much attention of researchers recently. However, most of the existing methods focus ...on addressing the task of nonoverlapping community detection, where each node must belong to one and only one community. In fact, communities are often overlapped with each other in many real-world networks, thus it is necessary to design overlapping community detection algorithms. To this end, this paper proposes a mixed representation-based MOEA (MR-MOEA) for overlapping community detection. In MR-MOEA, a mixed individual representation scheme is proposed to fast encode and decode the overlapping divisions of complex networks. Specifically, this mixed representation consists of two parts: one represents all potential overlapping nodes and the other delegates all nonoverlapping nodes. These two parts evolve together to detect the overlapping communities of networks based on different updating strategies suggested in MR-MOEA. We verify the effectiveness of the proposed algorithm MR-MOEA on ten real-world complex networks and the experimental results demonstrate that MR-MOEA is superior over six representative algorithms for overlapping community detection.
miRNAs belong to small non-coding RNAs that are related to a number of complicated biological processes. Considerable studies have suggested that miRNAs are closely associated with many human ...diseases. In this study, we proposed a computational model based on Similarity Constrained Matrix Factorization for miRNA-Disease Association Prediction (SCMFMDA). In order to effectively combine different disease and miRNA similarity data, we applied similarity network fusion algorithm to obtain integrated disease similarity (composed of disease functional similarity, disease semantic similarity and disease Gaussian interaction profile kernel similarity) and integrated miRNA similarity (composed of miRNA functional similarity, miRNA sequence similarity and miRNA Gaussian interaction profile kernel similarity). In addition, the
L
2
regularization terms and similarity constraint terms were added to traditional Nonnegative Matrix Factorization algorithm to predict disease-related miRNAs. SCMFMDA achieved AUCs of 0.9675 and 0.9447 based on global Leave-one-out cross validation and five-fold cross validation, respectively. Furthermore, the case studies on two common human diseases were also implemented to demonstrate the prediction accuracy of SCMFMDA. The out of top 50 predicted miRNAs confirmed by experimental reports that indicated SCMFMDA was effective for prediction of relationship between miRNAs and diseases.
With the rapid development of Internet of Things (IoT) technology, IoT devices have been widely used to collect physiological health data and provide diversified services to the terminal users. ...However, traditional data storage and sharing scheme cloud computing based in IoT face many challenges. For example, IoT devices are usually resource‐constrained (storage, computing power, battery capacity, etc.), data signed by IoT devices to ensure data integrity and authenticity will consume a lot of computing resources of IoT devices. At the same time, there is the challenge of high latency and unsafe data storage and sharing. To overcome these challenges, we propose a secure and efficient data storage and sharing scheme for blockchain‐based mobile‐edge computing. In our scheme, we construct the unique signature private key in a region into multiple key shares. IoT devices only need to submit the data and the random key shares allocated to the edge node. Edge node uses the recovered signature private key to realize data signature and homomorphic encryption. At the same time, the edge node will process timely data and return to the user. For data that need to be uploaded to the cloud for analysis, we use backup uploads to avoid data floods. Through experiments, it was found that our scheme can not only realize low‐latency message response for the terminal users, but also realize anonymous identity verification while ensuring data integrity and authenticity. The key shares of the signature private key are stored in different blocks of the blockchain to improve fault tolerance. The content extraction signature algorithm ensures that the key shares stored in different blocks are publicly verifiable. Safety analysis and performance analysis verify the feasibility and effectiveness of our scheme.
IoT devices submit data and share of keys. Trusted proxy nodes implement data signatures and homomorphic encryption to ensure data integrity and protect privacy, at the same time, this scheme reduces the burden of resource‐constrained IoT devices. Blockchain is used to store data index and key share to achieve tamper resistance and enhance fault tolerance.
Esophageal cancer has a poor prognosis and high mortality rate across the world. The diagnosis and treatment of esophageal cancer are hindered by the limited knowledge about the pathogenesis ...mechanisms of esophageal cancer. Esophageal cancer has two major subtypes, squamous and adenocarcinoma. In this work, we proposed a method to select candidate biomarkers of esophageal squamous carcinoma based on the topological differential analysis between the gene-gene interaction networks for esophageal squamous carcinoma and normal cells. We established the gene-gene interaction networks for esophageal squamous carcinoma and normal based on the correlation of genes. For each gene, we firstly calculated and compared five centrality measures, which could reflect the topological property of a network. According to five centrality measures, the genes with large differences between the two networks were regarded as candidate biomarkers for esophageal squamous carcinoma. A total of 21 candidate biomarkers were identified for esophageal squamous carcinoma, and seven of them have been confirmed to be biomarkers of esophageal-12 squamous carcinoma by previous research. In addition, six genes (
,
,
,
,
and
) were likely to be the biomarkers of tumorigenesis for esophageal squamous carcinoma due to the fact that the biological processes in which they participate are closely related with the development of esophageal squamous carcinoma. Statistical analysis indicates that effectiveness of the detected biomarkers of esophageal squamous carcinoma. The proposed method could be extended to other complex diseases for detecting the molecular features of pathopoiesis and targets for targeted therapy.
China's food production has increased 6-fold during the past half-century, thanks to increased yields resulting from the management intensification, accomplished through greater inputs of fertilizer, ...water, new crop strains, and other Green Revolution's technologies. Yet, changes in underlying quality of soils and their effects on yield increase remain to be determined. Here, we provide a first attempt to quantify historical changes in inherent soil productivity and their contributions to the increase in yield.
The assessment was conducted based on data-set derived from 7410 on-farm trials, 8 long-term experiments and an inventory of soil organic matter concentrations of arable land.
Results show that even without organic and inorganic fertilizer addition crop yield from on-farm trials conducted in the 2000s was significantly higher compared with those in the 1980s - the increase ranged from 0.73 to 1.76 Mg/ha for China's major irrigated cereal-based cropping systems. The increase in on-farm yield in control plot since 1980s was due primarily to the enhancement of soil-related factors, and reflected inherent soil productivity improvement. The latter led to higher and stable yield with adoption of improved management practices, and contributed 43% to the increase in yield for wheat and 22% for maize in the north China, and, 31%, 35% and 22% for early and late rice in south China and for single rice crop in the Yangtze River Basin since 1980.
Thus, without an improvement in inherent soil productivity, the 'Agricultural Miracle in China' would not have happened. A comprehensive strategy of inherent soil productivity improvement in China, accomplished through combining engineering-based measures with biological-approaches, may be an important lesson for the developing world. We propose that advancing food security in 21st century for both China and other parts of world will depend on continuously improving inherent soil productivity.