Search

The important role of microRNA (miRNA) in human diseases has been confirmed by some studies. However, only using biological experiments has greater blindness, leading to higher experimental costs. In this paper a high-efficiency algorithm based on a variety of biological source information and applying a combination of a convolutional neural network (CNN) feature extractor and an extreme learning machine (ELM) classifier is proposed. Specifically, the semantic similarity of diseases, the gaussian interaction profile kernel similarity of the four biological information of miRNA, disease, long non-coding RNA (lncRNA) and environmental factors (EFs), and the similarities of miRNAs are fused together. Among them, miRNAs similarity is composed of miRNA target information, sequence information, family information, and function information. Then, the dimensionality of the data set is reduced by the autoencoder (AE). Finally, deep features are extracted through CNN, and then the association between miRNA and disease is predicted by ELM. The experimental results show that the average AUC value based on the multi-biological source information (MSCNE) model is 0.9630, which can reach higher performance than the other classic classifier, feature extractor mentioned and the other existing algorithms. The results show the MSCNE algorithm is effective to predict the correlation of miRNA-disease.

Mobile edge computing (MEC) is an emergent architecture, which brings computation and storage resources to the edge of mobile network and provides rich services and applications near the end users. The joint problem of task offloading and resource allocation in the multi-user collaborative mobile edge computing network (C-MEC) based on Orthogonal Frequency-Division Multiple Access (OFDMA) is a challenging issue. In this paper, we investigate the offloading decision, collaboration decision, computing resource allocation and communication resource allocation problem in C-MEC. The delay-sensitive tasks of users can be computed locally, offloaded to collaborative devices or MEC servers. The goal is to minimize the total energy consumption of all mobile users under the delay constraint. The problem is formulated as a mixed-integer nonlinear programming (MINLP), which involves the joint optimization of task offloading decision, collaboration decision, subcarrier and power allocation, and computing resource allocation. A two-level alternation method framework is proposed to solve the formulated MINLP problem. In the upper level, a heuristic algorithm is used to handle the collaboration decision and offloading decisions under the initial setting; and in the lower level, the allocation of power, subcarrier, and computing resources is updated through deep reinforcement learning based on the current offloading decision. Simulation results show that the proposed algorithm achieves excellent performance in energy efficient and task completion rate (CR) for different network parameter settings.

A growing number of studies have confirmed the important role of microRNAs (miRNAs) in human diseases and the aberrant expression of miRNAs affects the onset and progression of human diseases. The discovery of disease-associated miRNAs as new biomarkers promote the progress of disease pathology and clinical medicine. However, only a small proportion of miRNA-disease correlations have been validated by biological experiments. And identifying miRNA-disease associations through biological experiments is both expensive and inefficient. Therefore, it is important to develop efficient and highly accurate computational methods to predict miRNA-disease associations. A miRNA-disease associations prediction algorithm based on Graph Convolutional neural Networks and Principal Component Analysis (GCNPCA) is proposed in this paper. Specifically, the deep topological structure information is extracted from the heterogeneous network composed of miRNA and disease nodes by a Graph Convolutional neural Network (GCN) with an additional attention mechanism. The internal attribute information of the nodes is obtained by the Principal Component Analysis (PCA). Then, the topological structure information and the node attribute information are combined to construct comprehensive feature descriptors. Finally, the Random Forest (RF) is used to train and classify these feature descriptors. In the five-fold cross-validation experiment, the AUC and AUPR for the GCNPCA algorithm are 0.983 and 0.988 respectively.

Geographic routing is a research hotspot of the Internet of Vehicles (IoV) and intelligent traffic system (ITS). In practice, the vehicle movement is not only affected by its characteristics and the relationship between the vehicle and position but also affected by some implicit factors. Pointing to this problem, we combine the vehicle moving position probability matrix, the vehicle position association matrix, and the implicit factors to study the influence of vehicle position potential features and vehicle association potential features and propose a routing algorithm based on vehicle position (RAVP) analysis, which can obtain the more accurate vehicle prediction trajectory. Then, the vehicle distance is obtained based on the vehicle prediction trajectory. By the normalization of vehicle distance and cache, the vehicle data forwarding capability is obtained and the transmission decision is made. Simulation results show that the proposed algorithm outperforms the other three routing algorithms in terms of packet delivery ratio, average end-to-end delay, and routing overhead ratio.

The mode selection and resource allocation are important issues in Device-to-Device (D2D) communication, which have been investigated in single Base Station (BS) cellular network. However, the joint problem of the base station selection, mode selection and resource allocation is a challenging issue. Because the mode selection, base station and resource allocation are inter-coupled with each other. The joint problem of D2D User Equipments (DUEs) mode selection, base station selection, channel allocation and power allocation remains an open problem. In this paper, the scenario with multiple BSs in D2D heterogeneous networks is considered, and the joint problem of DUEs mode selection, base station selection, channel allocation and power allocation is studied. The objective is to maximize the system energy efficiency. We consider the DUEs multiplex the cellular user uplink resource. Meanwhile, the constraint of the total transmission power of the DUEs, and the constraint of the load balancing of the BSs are considered. The joint problem of mode selection, base station selection and resource allocation is formulated. The formulated problem is a non-convex mixed-integer optimization problem. In order to handle the formulated problem, a joint mode selection, base station selection and resource allocation algorithm based on particle swarm optimization is proposed. Numerical results demonstrate that the proposed algorithm can improve the system energy efficiency and obtain the desired target.

Background The existing studies show that circRNAs can be used as a biomarker of diseases and play a prominent role in the treatment and diagnosis of diseases. However, the relationships between the vast majority of circRNAs and diseases are still unclear, and more experiments are needed to study the mechanism of circRNAs. Nowadays, some scholars use the attributes between circRNAs and diseases to study and predict their associations. Nonetheless, most of the existing experimental methods use less information about the attributes of circRNAs, which has a certain impact on the accuracy of the final prediction results. On the other hand, some scholars also apply experimental methods to predict the associations between circRNAs and diseases. But such methods are usually expensive and time-consuming. Based on the above shortcomings, follow-up research is needed to propose a more efficient calculation-based method to predict the associations between circRNAs and diseases. Results In this study, a novel algorithm (method) is proposed, which is based on the Graph Convolutional Network (GCN) constructed with Random Walk with Restart (RWR) and Principal Component Analysis (PCA) to predict the associations between circRNAs and diseases (CRPGCN). In the construction of CRPGCN, the RWR algorithm is used to improve the similarity associations of the computed nodes with their neighbours. After that, the PCA method is used to dimensionality reduction and extract features, it makes the connection between circRNAs with higher similarity and diseases closer. Finally, The GCN algorithm is used to learn the features between circRNAs and diseases and calculate the final similarity scores, and the learning datas are constructed from the adjacency matrix, similarity matrix and feature matrix as a heterogeneous adjacency matrix and a heterogeneous feature matrix. Conclusions After 2-fold cross-validation, 5-fold cross-validation and 10-fold cross-validation, the area under the ROC curve of the CRPGCN is 0.9490, 0.9720 and 0.9722, respectively. The CRPGCN method has a valuable effect in predict the associations between circRNAs and diseases.

With the rapid increase of smart mobile devices and the improvement of people's demand for wireless communication, the insufficient system capacity and shortage of spectrum resources is gradually emerging. The current wireless communication technology is facing enormous challenges. Device-to-Device (D2D) technology has become a key technology in the future 5G network, with its flexible working mode, low energy consumption, low latency and high capacity, etc. At the same time, D2D communication devices are usually powered by batteries and have a limited lifetime. The lack of spectrum resources and the single power supply for D2D User Equipment (DUE) have become an important issue for mobile communication. Energy harvesting (EH) can provide the power supply. The joint problem of mode selection and resource allocation is challenging issues in energy harvesting D2D heterogeneous networks (EH-DHNs). In this paper, mode selection and resource allocation problem with DUEs multiplexing cellular user equipments (CUEs) uplink spectrum resources for EH-DHNs is investigated. Our object is to maximize the system throughput, and the energy harvesting constraint and the quality of service of CUEs are considered. In order to tackle these issues. The mode selection and resource allocation system throughput maximization problem in EH-DHN is formulated. The formulated problem is solved by the convex optimization theory and greedy strategy. We proposed a Mode Selection and Resource Allocation algorithm (MSRA). In order to illustrate the advantage of the MSRA algorithm, we compared it with other algorithms. We also analyzed the convergence of the MSRA and the performance with different system configurations on system throughput. Comparison shows that the MSRA algorithm can improve system throughput effectively.

Cognitive radio (CR) is a state-of-the-art technology to solve the spectrum shortage problem for emerging wireless services, which include the CR-enabled vehicular ad hoc networks (CR-VANETs) for vehicle-to-road side unit (RSU) communications. With the increasing demands for high data rate and more reliable mobile services, orthogonal frequency division multiple access (OFDMA) has been often used in such systems. Energy efficiency is an important issue in OFDMA CR-VANETs due to the concern of green communications to transmit the required data in the shortest time, without affecting primary users. In this paper, we proposed an adaptive solution to minimize the overall energy consumption of CR-VANETs as well as maintaining the service quality of Vehicle-to-RSU uplink communications. This goal has been achieved by the means of dynamically selecting different spectrum access schemes for CR-enabled vehicles with relays. Considering the inter-vehicle distances and location information, we formulated a mixed-integer nonlinear constrained optimization problem. A heuristic algorithm based on the greedy strategy and bisection method is then used to solve the formulated problem and it has been evaluated through extensive simulations for different upload data sizes and available communication durations. The acquired results substantiate the efficiency of the proposed solution in terms of energy consumption.

The mode selection and resource allocation are important issues in device-to-device (D2D) communication. There are very little research works considering the joint problem of base station selection and load balance of base station with mode selection and base station selection in multiple BSs cellular systems or heterogeneous cellular systems, which is a challenging issue. In this paper, the joint problem of D2D User Equipments (DUEs) mode selection, base station selection, channel allocation and power allocation is investigated. A mode selection, base station selection and resource allocation problem is formulated. The goal is to maximize the system energy efficiency. We consider the DUEs multiplex the cellular user uplink resource. Meanwhile, the total transmission power constraint of the DUEs, and the load balancing constraint of the BSs are considered. The formulated problem is NP problem, which is hard to solve. In order to solve the formulated problem effectively, a joint mode selection, base station selection and resource allocation algorithm based on particle swarm optimization (PSO) is proposed. Numerical results demonstrate that the proposed algorithm can effectively improve the system energy efficiency.

Mobile edge computing (MEC) is a promising technique to enhance the computation capacity at the edge of mobile networks. The joint problem of partial offloading decision, offloading scheduling and resource allocation for MEC systems is a challenge issue. In this paper, we investigate the problem of partial offloading scheduling and resource allocation for mobile edge computing systems with multiple independent tasks. Our goal is to minimize the weighted sum of the execution delay and energy consumption while guaranteeing the transmission power constraints of the tasks. The execution delay of tasks running in MEC and mobile edge devices are both considered. The energy consumption of both the tasks computing and task data transmission are considered as well. In order to tackle these issues, we formulate an energy-efficient and low-delay partial offloading scheduling and power allocation problem in single-user MEC systems, which is a non-convex mixed-integer optimization problem. A two-level alternation method framework based on decomposition optimization strategy is proposed. Furthermore, we propose Joint Partial Offloading scheduling and power Allocation (JPOA) iterative algorithm based on Lagrangian constrained optimization and Johnson method. Numerical results demonstrate JPOA algorithm achieves the most noticeable delay performance with a large energy consumption reduction.

A data streams synopses structure FPCBF, which is based on bloom filter, is proposed in this paper. Each unit of vector BF[e] in FPCBF is a two-tuples. The transactions insert operation (InsertTran) and 1-frequent patterns pregeneration operation (PreGenFP) is defined. Then, A data streams frequent patterns mining algorithm BFFPM which is based on FPCBF is proposed in this paper. The BFFPM algorithm contains two parts: 1-frequent patterns generation and r-frequent patterns generation. The problem of computing the 1-frequent patterns generation is transformed into the problem of computing the longest common sub-sequence α i LCS of k setting identifier sequence in BF[e] in FPCBF. In the same way, the problem of computing the r-frequent patterns generation is transformed into the problem of computing the longest common sub-sequence LCS r , which is the longest common sequence of the identifier sequence α i LCS ,…, i r LCS α + of r items. The IBM synthesizes data generation which output customers shopping a data are adopted as experiment data. The FPCBF algorithm not only has high precision for mining frequent patterns, but also has low memory requirement

Routing and spectrum allocation is an important challenge in cognitive wireless mesh networks. A distributed routing and spectrum allocation algorithm with cooperation (DRSAC-W) in cognitive wireless mesh networks is proposed in this paper. In order to show the decrease of the average end-to-end delay with cooperation in DRSAC-W, a distributed routing and spectrum allocation algorithm without cooperation (DRSAC-WO) is proposed in this paper. Minimizing the average end-to-end delay is the objective of DRSAC-W and DRSAC-WO. Simulation results show that the proposed algorithm DRSAC-W with cooperation can alleviate the high delay due to the heterogeneity of available channels of different nodes and achieve low average end-to-end delay.