Search

The synchronization problem of multi-agent systems with non-identical general agents under time-varying topologies and in the presence of external disturbances has not been solved for the introspective agents, i.e., agents have access to parts of their own states. This paper aims to tackle this problem. It is assumed that the time-varying topology switches among a certain amount of topologies with any a priori given dwell time and each topology contains a directed spanning tree. This paper proposes a family of distributed protocols for each agent only using relative information from its neighboring agents and some of its own states, such that synchronization can be achieved among agents while the effect of disturbances with finite power on the norm of all agents' output disagreement can be suppressed as much as possible. It should be emphasized that agents' controller states are exempted from the protocol design. [ABSTRACT FROM AUTHOR]

Featured Application: The proposed algorithms could be integrated into mobile router platforms installed in public transportation vehicles which can provide high-speed internet connectivity to the passengers and the equipment of the vehicles. The proposed algorithms also could be integrated into Access Points (APs) serving (possibly temporarily installed) small cells, APs that do not have dedicated backhaul connections, and the wireless links of some macro cells being used as backhaul connections. 5G wireless networks have as one of the main characteristics the large-scale deployment of small cells (microcells, picocells, etc.), which is expected to bring several advantages in what concerns the high speed and low latency connectivity of the users. This large-scale deployment of small cells also raises several technical challenges, provisioning the backhaul connectivity being one of them. The paper considers the situations when small cells are deployed temporarily or are deployed in a vehicle transporting many passengers, situations when the traditional wired or wireless backhaul solutions could be too costly to be used. The paper proposes, as an alternative solution, the use as backhaul connections of the wireless links set up in the macro cells which cover the location of the small cell. The paper proposes several Game Theory (GT)-based Load-Balancing (LB) algorithms for distributing the traffic of the small cell users over the macro cell links. The proposed LB algorithms are evaluated by computer simulations and are compared with "classical" LB algorithms considered as references. The performed computer simulations show that the auction-based algorithms have the best performance in terms of delay suffered by the transmitted data packets, while the selfish routing type algorithm has weaker performance, even behaving poorly than some of the reference non-GT-based algorithms. The paper also considers the situation when several small cell APs are deployed in a limited area or a vehicle and the user groups that attach to different APs should be identified. The paper proposes two GT-based user clustering algorithms, and the performance of these algorithms are evaluated by computer simulations. These simulations show that even simple clustering algorithms could improve the distribution of the traffic over the neighbor small cell APs and reduce the delay experienced by the data packets in the transmission system. [ABSTRACT FROM AUTHOR]

Objectively evaluating representative papers in a specific scientific research field is of great significance to the development of academia and scientific research institutions. Representative papers on achievements in scientific research can reflect the academic level and research characteristics of researchers and research institutions. The existing research methods are mainly based on external feature indicators and citation analysis methods, and the method of combining artificial intelligence is in its infancy. From the perspective of scientific research institutions, this paper proposes a graph autoencoder framework based on heterogeneous networks for the measurement of paper impact, named GAEPIM. Specifically, we propose two versions of GAEPIM based on a graph convolutional network and graph transformer network. The models rank papers in a specific research field and find the most representative papers and their scientific institutions. The proposed framework constructs a heterogeneous network of papers, institutions, and venues and simultaneously analyzes the semantic information of papers and the heterogeneous network structural information. Finally, based on the complex network information diffusion model, the proposed method performs better than several widely used baseline methods. [ABSTRACT FROM AUTHOR]

The heterogeneous network (HetNet) is a specified cellular platform to tackle the rapidly growing anticipated data traffic. From a communications perspective, data loads can be mapped to energy loads that are generally placed on the operator networks. Meanwhile, renewable energy-aided networks offer to curtailed fossil fuel consumption, so to reduce the environmental pollution. This paper proposes a renewable energy based power supply architecture for the off-grid HetNet using a novel energy sharing model. Solar photovoltaics (PV) along with sufficient energy storage devices are used for each macro, micro, pico, or femto base station (BS). Additionally, a biomass generator (BG) is used for macro and micro BSs. The collocated macro and micro BSs are connected through end-to-end resistive lines. A novel-weighted proportional-fair resource-scheduling algorithm with sleep mechanisms is proposed for non-real time (NRT) applications by trading-off the power consumption and communication delays. Furthermore, the proposed algorithm with an extended discontinuous reception (eDRX) and power saving mode (PSM) for narrowband internet of things (IoT) applications extends the battery lifetime for IoT devices. HOMER optimization software is used to perform optimal system architecture, economic, and carbon footprint analyses while the Monte-Carlo simulation tool is used for evaluating the throughput and energy efficiency performances. The proposed algorithms are validated through the practical data of the rural areas of Bangladesh from which it is evident that the proposed power supply architecture is energy-efficient, cost-effective, reliable, and eco-friendly. [ABSTRACT FROM AUTHOR]

Reports have shown that the demand for data managed by wireless systems is expected to grow by more than 500 exabytes by 2025 and beyond. 5G networks are predicted to meet these demands, provided that the spectrum resources are well managed. In this paper, an enhanced dynamic spectrum allocation (E-DSA) method is proposed, which incorporates a cooperative type of game theory called the Nash bargaining solution (NBS). It was assumed that there is one primary user (PU) and two secondary users (SU) in the network and their spectrum allocation was analyzed by testing the validity of the algorithm itself by using price weight factors to control the costs of the spectrum sharing. The solution was established by combining a proposed multiplexing method called the Filter Bank Multicarrier (FBMC) for 5G configuration, with the E-DSA algorithm to maximize the throughput of a heterogeneous 5G network. It was shown that the throughputs for 5G with EDSA implementation were always higher than those of the ones without E-DSA. The simulation was done using the LabVIEW communication software and was analyzed based on a 5G urban macro and micro network configuration to validate the heterogeneity of the network. [ABSTRACT FROM AUTHOR]

Session-based recommendation aims to predict the next item to be interacted by a specific type of behavior (e.g., click or purchase) within a session. However, the main challenge comes from the lack of interactions in the target behavior. Despite state-of-the-art approaches aim to alleviate this issue by incorporating auxiliary behaviors through multi-behavior modeling, they are still weak in supporting cold-start recommendation due to the limited generalization ability. Having witnessed the effectiveness of meta-optimized models for few-shot learning, in this paper, we propose a memory-augmented meta-learning framework for session-based target behavior recommendation. It adopts meta-learning to learn well-generalized global sharing initialization parameters for all sessions, and derives personalized local parameters for each session through fine-tuning. Particularly, we first extract multi-behavior characteristics to derive dynamic user intentions within a session. Then we apply soft-clustering in meta-learning based on well-designed memory structures, so that multi-behavior sessions with similar intention could share related knowledge. The experimental results on two datasets show that our MMFSR model effectively outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Rule mining is an important and challenging task in data mining. Although many state-of-art algorithms have been proposed on dense data, they are not effectively adaptive for sparse data, such as sparse heterogeneous networks. Transfer learning improves the performance of algorithms in the target domain by transferring knowledge from a similar source domain, which provides a feasible and effective method to solve the above challenge. In this paper, we propose a transfer learning-based algorithm to mine rules on sparse data effectively, named TL-ERMSD. The algorithm is capable of detecting the knowledge of a common structure as well as the rules and logics between the source and target domains. Then, rule transfer is carried out by establishing the mapping mechanism between the two domains. We conducted experiments over the heterogeneous network datasets, including the source domain dataset FB15K and the target domain dataset Yago2Sample. The results demonstrate that the proposed TL-ERMSD for rule mining has a significant advantage over the existing algorithms. [ABSTRACT FROM AUTHOR]

Location-based social networks (LBSNs) have greatly promoted the development of the field of human mobility mining. However, the sparsity, multimodality and heterogeneity nature of the user check-in data remains a great concern for learning high-quality user or other entity representations, especially in the downstream application tasks, such as point-of-interest (POI) recommendation. Most existing methods focus on user preference modeling based on sequential POI tags without exploring the interaction between different modalities (e.g., user-user interactions, user-timestamp interactions, user-POI interactions, etc.). To this end, we introduce a multimodal interaction aware embedding framework to generate reliable entity embeddings on the heterogeneous socio-spatial network. At its core, first, multi-modal interaction sub-graph sampling techniques are designed to capture the heterogeneous contexts; then, a self-supervised contrastive learning technique is leveraged to extract intra-modality and inter-modality interactions in a light way. We conduct experiments on the next-POI recommendation tasks based on three real-world datasets. Experimental results demonstrate the superiority of our model over the state-of-the-art embedding learning algorithms. [ABSTRACT FROM AUTHOR]

Media with partisan tendencies publish news articles to support their preferred political parties to guide the direction of public opinion. Therefore, discovering political bias in news texts has important practical significance for national election prediction and public opinion management. Some biased news often has obscure expressions and ambiguous writing styles. By bypassing the language model, the accuracy of methods that rely on news semantic information for position discrimination is low. This manuscript proposes a news standpoint discrimination method based on social background information fusion heterogeneous network. This method expands the judgment ability of creators and topics on news standpoints from external information and fine-grained topics based on news semantics. Multi-attribute features of nodes enrich the feature representation of nodes, and joint representation of heterogeneous networks can reduce the dependence of position discrimination on the news semantic information. To effectively deal with the position discrimination of new news, the design of a multi-attribute fusion heterogeneous network is extended to inductive learning, avoiding the cost of model training caused by recomposition. Based on the Allsides dataset, this manuscript expands the information of its creator's social background and compares the model for discriminating political positions based on news content. In the experiment, the best transductive attribute fusion heterogeneous network achieved an accuracy of 92.24% and a macro F1 value of 92.05%. The effect is improved based purely on semantic information for position discrimination, which proves the effectiveness of the model design. [ABSTRACT FROM AUTHOR]

The work‐flow is emerging as the promising paradigm for the different computing infrastructures of distributed nature. It is applied widely in various scientific fields and simple job execution. To manage with the enormous flow of data in the work‐flow, the requirement of huge infrastructure and the execution in the reasonable time. The work ‐flow adapts to the cloud environment. Though cloud environment provides with the large‐scale infrastructure and consistency and efficiency on comparing to the system operated over non‐cloud, a proper scheduling is entailed for the execution of tasks satisfying the specified constraints with the necessary security measure that has to be provided as the cloud does not provide with the counter measures for the security threats. More over as the real world tasks are most probably heterogeneous requiring virtual machines of different instance of series. So the paper proffers a cost‐effective algorithm based on the multi‐populated genetic algorithm (Multi‐populated GA) implanted with particle swarm optimization (PSO) for the heterogeneous networks so as to minimize the cost of the execution and meet out the QOS constraints, the results serve as the guiding principle for the security level improvement for the (sensitive) critical tasks. The performance evaluation of the scheduling using the workflowsim is performed to evidence the maximum reduction in the cost of the execution and the QOS constraints met using the proposed system. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunications Science is the property of Beijing Xintong Media Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Predicting new therapeutic effects (drug repositioning) of existing drugs plays an important role in drug development. However, traditional wet experimental prediction methods are usually time-consuming and costly. The emergence of more and more artificial intelligence-based drug repositioning methods in the past 2 years has facilitated drug development. In this study we propose a drug repositioning method, VGAEDR, based on a heterogeneous network of multiple drug attributes and a variational graph autoencoder. First, a drug-disease heterogeneous network is established based on three drug attributes, disease semantic information, and known drug-disease associations. Second, low-dimensional feature representations for heterogeneous networks are learned through a variational graph autoencoder module and a multi-layer convolutional module. Finally, the feature representation is fed to a fully connected layer and a Softmax layer to predict new drug-disease associations. Comparative experiments with other baseline methods on three datasets demonstrate the excellent performance of VGAEDR. In the case study, we predicted the top 10 possible anti-COVID-19 drugs on the existing drug and disease data, and six of them were verified by other literatures. [ABSTRACT FROM AUTHOR]

Personalized recommendation has become indispensable in today's information society. Personalized recommendations play a significant role for both information producers and consumers. Studies have shown that probability matrix factorization can improve personalized recommendation performance. However, most probability matrix factorization models ignore the effect of item-implicit association and user-implicit similarity on recommendation performance. To overcome this lack, we propose a recommendation model based on probability matrix factorization that considers the correlation of user rating items. Our model uses the resource allocation of the bipartite graphs and the random walk of meta-paths in heterogeneous networks to determine the implicit association of items and the implicit similarity of users, respectively. Thus, the final item association and user similarity are obtained. The final item and user similarity relationships are integrated into the probability matrix factorization model to obtain the user's prediction score for a specific project. Finally, we validated the model on the Delicious-2k, Movielens-2k and last.fm-2k datasets. The results show that our proposed algorithm model has higher recommendation accuracy than other recommendation algorithms. [ABSTRACT FROM AUTHOR]

In vehicular communication, high mobility causes frequent signal variation, which results in frequent handover and poor quality of service for vehicular users. Installing a relay on the top of the vehicle is a promising technology for overcoming these issues because these relays compensate the Vehicle Penetration Loss. Also, due to the deployment of next-generation networks and low-power nodes, network density and heterogeneity are increasing. As a result, interference is also increasing. Therefore, in the past, the performance of cooperative user in vehicular scenarios was analyzed using an amplify-and-forward (AF) mode based half-duplex (HD) relay in a heterogeneous network (HetNet). But the performance of HD relay is limited due to transmission capacity and bandwidth efficiency. In this paper, we use the AF mode based full-duplex (FD) relay in HetNet to analyze the performance of cooperative user in terms of coverage probability and outage capacity and, we compare the results with the AF mode based HD relay in vehicular scenario. Simulation results show that the performance of the FD relay depends on residual self-interference (RSI) in HetNet, and it outperforms the HD relay for the low value of RSI. The results are analyzed using both the analytical method and Monte Carlo simulation. These results provide the theoretical support for the deployment of relays in next-generation networks with high mobility scenario. [ABSTRACT FROM AUTHOR]

The IEEE 802.11be (Wi-Fi 7) standard for WLANs, which is currently under development, will allow for a multiple throughput increase and lower latency in comparison with the previous IEEE 802.11ax (Wi-Fi 6) standard. One of the main novelties of IEEE 802.11be to achieve this is the native support for the multi-link feature, and this can be done using single or multiple radio interfaces. When using one radio interface, the device can quickly switch it from a busy channel to a free one and consequently reduce the channel access delay. However, transmission can only be performed in one channel. The usage of multiple radio interfaces allows for simultaneous data transmission on multiple channels, but the radio interfaces can interfere with each other, so the standard describes an operation mode for the mitigation of such interference. In this multiple channels operation mode, one performs either joint synchronized transmission or joint synchronized signal reception. The article describes algorithms for switching a single radio interface of a multi-link device, which allow to increase its throughput. It also compares the performance of multi-link devices with one and several radio interfaces. [ABSTRACT FROM AUTHOR]

Background: Drug repositioning is a very important task that provides critical information for exploring the potential efficacy of drugs. Yet developing computational models that can effectively predict drug–disease associations (DDAs) is still a challenging task. Previous studies suggest that the accuracy of DDA prediction can be improved by integrating different types of biological features. But how to conduct an effective integration remains a challenging problem for accurately discovering new indications for approved drugs. Methods: In this paper, we propose a novel meta-path based graph representation learning model, namely RLFDDA, to predict potential DDAs on heterogeneous biological networks. RLFDDA first calculates drug–drug similarities and disease–disease similarities as the intrinsic biological features of drugs and diseases. A heterogeneous network is then constructed by integrating DDAs, disease–protein associations and drug–protein associations. With such a network, RLFDDA adopts a meta-path random walk model to learn the latent representations of drugs and diseases, which are concatenated to construct joint representations of drug–disease associations. As the last step, we employ the random forest classifier to predict potential DDAs with their joint representations. Results: To demonstrate the effectiveness of RLFDDA, we have conducted a series of experiments on two benchmark datasets by following a ten-fold cross-validation scheme. The results show that RLFDDA yields the best performance in terms of AUC and F1-score when compared with several state-of-the-art DDAs prediction models. We have also conducted a case study on two common diseases, i.e., paclitaxel and lung tumors, and found that 7 out of top-10 diseases and 8 out of top-10 drugs have already been validated for paclitaxel and lung tumors respectively with literature evidence. Hence, the promising performance of RLFDDA may provide a new perspective for novel DDAs discovery over heterogeneous networks. [ABSTRACT FROM AUTHOR]

Erasure codes offer a storage-efficient redundancy mechanism for maintaining data availability guarantees in storage clusters, yet also incur high network traffic consumption and recovery time in failure repair. Extensive research has been carried out to reduce the recovery time. However, previous works either target specific erasure code constructions which are not commonly used in today’s distributed storage clusters or neglect the heterogeneous bandwidth property in real network environments. Since erasure-coded clusters are typically composed of multi-node with heterogeneous bandwidth and accessed in parallel, the whole recovery time is mainly restricted by the low-bandwidth links. In this article, we propose SMFRepair, a single-node multi-level forwarding repair technique that is designed to improve the performance in heterogeneous networks based on Reed-Solomon codes for general fault tolerance. SMFRepair carefully selects the helper nodes and uses idle nodes to bypass low-bandwidth links. Idle nodes have sufficient and unused network bandwidth. It also pipelines the repair links that are optimized by idle nodes. Furthermore, a multi-node scheduling repair technique, called MSRepair, is proposed. MSRepair carefully schedules the multi-node repair link to saturate the most unoccupied bandwidth and transfers data from as large-bandwidth links as possible, with the primary objective of minimizing the recovery time. Large-scale simulation and Amazon EC2 real experiments show that compared to state-of-the-art repair techniques, SMFRepair can accelerate the single-node recovery by up to 47.69%, and MSRepair can reduce the multi-node recovery time by 33.78% $\sim$ ∼ 67.53%. [ABSTRACT FROM AUTHOR]

Traffic congestion has been one of the major performance limiting factors of heterogeneous networks (HetNets). There have been several load balancing schemes put up to solve this by balancing load among base stations (BSs), but they appear to be unfeasible due to the complexity required and other unsatisfactory performance aspects. Cell range extension (CRE) has been a promising technique to overcome this challenge. In this paper, a permutation based CRE technique is proposed to find the best possible formation of bias for BSs to achieve load balance among BSs. In comparison to the baseline scheme, results depict that the suggested method attains superior performance in terms of network load balancing and average throughput. The complexity of the suggested algorithm is considerably reduced in comparison to the proposed permutation based CRE method it is further modified from. [ABSTRACT FROM AUTHOR]

Consumer behaviors (e.g., clicking products, adding products to favorites, adding products to carts, and purchasing products) play important roles in inferring consumers' interests for product recommendation. Although studies have been conducted to incorporate the consumer behaviors for product recommendation, the heterogeneity of the behaviors and their composites were seldom explored for product recommendation. There is a need to capture the heterogeneity of the consumer behaviors and reveal their importance in the product recommendation because the behaviors indicate different consumer preferences for products. To bridge the gap, this research proposes a heterogeneous network-based approach to leverage the consumer behaviors for product recommendation. The proposed approach represents consumers and products as different types of nodes and behaviors as different types of edges. Meta paths that describe behavioral relationships between the consumers and products are used to calculate their similarities, which are further used to generate recommendations. To select informative meta paths for product recommendation, a heuristic selection mechanism is proposed. Besides, the research uses a non-negative matrix factorization method to learn the weights of the selected meta paths and then makes personalized recommendations for consumers. Experimental results based on real-world data demonstrate that the proposed approach not only helps to understand the roles of different consumer behaviors in product recommendation, but also achieves better recommendation performance than several baseline methods. [ABSTRACT FROM AUTHOR]

Copyright of Informacije MIDEM: Journal of Microelectronics, Electronic Components & Materials is the property of MIDEM Society and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As the battery-operated power source of wireless sensor networks, energy consumption is a major concern. The medium-access protocol design solves the energy usage of sensor nodes while transmitting and receiving data, thereby improving the sensor network's lifetime. The suggested work employs a hybrid algorithm to improve the energy efficiency of sensor networks with nodes that are regularly placed. Every node in this protocol has three operating modes, which are sleep mode, receive mode, and send mode. Every node enters a periodic sleep state in order to conserve energy, and after waking up, it waits for communication. During the sleep mode, the nodes turn off their radios in order to reduce the amount of energy they consume while not in use. As an added feature, this article offers a channel access mechanism in which the sensors can send data based on the Logical Link Decision (LLD) algorithm and receive data based on the adaptive reception method. It is meant to select acceptable intermediary nodes in order to identify the path from the source to the destination and to minimize data transmission delays among the nodes in the network scenario. Aside from that, both simulation and analytical findings are used to examine the activity of the suggested MAC, and the created models are evaluated depending on their performance. With regard to energy consumption, latency, throughput, and power efficiency, the result demonstrates that the suggested MAC protocol outperforms the corresponding set of rules. The extensive simulation and analytical analysis showed that the energy consumption of the proposed LELLMAC protocol is reduced by 22% and 76.9% the end-to-end latency is 84.7% and 87.4% percent shorter, and the throughput is 60.3% and 70.5% higher than the existing techniques when the number of node is 10 and 100 respectively. [ABSTRACT FROM AUTHOR]

In order to solve the problem that incomplete mining of structural information and semantic information in heterogeneous networks, a link prediction method combining meta-path-based analysis and hidden Markov model was proposed for link prediction of heterogeneous network.Considering that clustering could effectively capture the structural information of heterogeneous network, the k-means algorithm was improved to obtain the initial clustering center method based on the minimum distance mean square error, and it was applied to the hidden Markov model, first-order cluster hidden markov model (C-HMM(1)) link prediction method, and a link prediction method for heterogeneous network with second-order cluster hidden Markov model (C-HMM(2)) were designed.Further, considering the feature information of the data, a link prediction method called ME-HMM that combined the maximum entropy model and the second-order Markov model was proposed.The experimental results show that the ME-HMM has higher link prediction accuracy than the C-HMM, and the ME-HMM method has better performance than the C-HMM method because it fully considers the feature information of the data.

An architecture named CoLoR (coupling service location and inter-domain routing) was introduced to securely and efficiently interconnect networks with different architectures (called heterogeneous networks below).First, the fundamental challenges and scientific problems that have to be addressed by CoLoR were raised.Then, the core aspects of CoLoR were described, including how to characterize and represent the cyberphysical system comprised by heterogeneous networks, the network architecture, the basic communication model and how secure internetworking was achieved.After that, results from prototype implementation were presented to demonstrate the feasibility and capability of CoLoR, including defending against attacks and preventing data leakage.Finally, some open issues were outlined for future studies.

Based on the reviews of standardizations and many other works of 5G-satellite integrated network (5GSIN), the research progress of 5GSIN key technologies, applications and network architectures were expounded and analyzed.Aiming at the key problems caused by the strong heterogeneity and large spatio-temporal scale of 5GSIN, the multi-layer distributed network architecture was proposed, and the architecture management method was designed.Finally, several key directions of the future development of 5GSIN were analyzed from the perspective of intelligence, in order to provide some references for research in related fields.

As a promising technology to improve spectrum efficiency and transmission coverage, Heterogeneous Network (HetNet) has attracted the attention of many scholars in recent years. Additionally, with the introduction of the Non-Orthogonal Multiple Access (NOMA) technology, the NOMA-assisted HetNet cannot only improve the system capacity but also allow more users to utilize the same frequency band resource, which makes the NOMA-assisted HetNet a hot topic. However, traditional resource allocation schemes assume that base stations can exactly estimate direct link gains and cross-tier link gains, which is impractical for practical HetNets due to the impact of channel delays and random perturbation. To further improve energy utilization and system robustness, in this paper, we investigate a robust resource allocation problem to maximize the total Energy Efficiency (EE) of Small-Cell Users (SCUs) in NOMA-assisted HetNets under imperfect channel state information. By considering bounded channel uncertainties, the robust resource optimization problem is formulated as a mixed-integer and nonlinear programming problem under the constraints of the cross-tier interference power of macrocell users, the maximum transmit power of small base station, the Resource Block (RB) assignment, and the quality of service requirement of each SCU. The original problem is converted into an equivalent convex optimization problem by using Dinkelbach's method and the successive convex approximation method. A robust Dinkelbach-based iteration algorithm is designed by jointly optimizing the transmit power and the RB allocation. Simulation results verify that the proposed algorithm has better EE and robustness than the existing algorithms.

The study of drug side effects is a significant task in drug discovery. Candidate drugs with unaccepted side effects must be eliminated to prevent risks for both patients and pharmaceutical companies. Thus, all side effects for any candidate drug should be determined. However, this task, which is carried out through traditional experiments, is time-consuming and expensive. Building computational methods has been increasingly used for the identification of drug side effects. In the present study, a new path-based method was proposed to determine drug side effects. A heterogeneous network was built to perform such method, which defined drugs and side effects as nodes. For any drug and side effect, the proposed path-based method determined all paths with limited length that connects them and further evaluated the association between them based on these paths. The strong association indicates that the drug has a side effect with a high probability. By using two types of jackknife test, the method yielded good performance and was superior to some other network-based methods. Furthermore, the effects of one parameter in the method and heterogeneous network was analyzed.

To reduce the base station energy consumption and co-channel interference in heterogeneous cellular networks, a joint optimization algorithm combined with energy harvesting and energy cooperation was proposed with the objective of energy efficiency optimization.First, a mixed-integer nonlinear programming problem for joint resource allocation was constructed considering the constraints of user service quality, the constraints of cellular base station power, and the constraints of renewable energy harvesting.Second, considering that the problem was an NP-hard problem which was difficult to solve directly, the complex original problem was decomposed into three subproblems, such as user association, power allocation, and energy cooperation, with the fixed-variable method, which were solved by using the Lagrangian pairwise method, particle swarm optimization algorithm, and matching theory, respectively.Finally, the final solution of the original problem was obtained by combining the above three algorithms through convergent iterative algorithms.The simulation results show that the proposed algorithm has improved convergence and system energy efficiency compared with the comparison algorithm.

This paper deals with cooperative output tracking problems for heterogeneous networks of linear agents. To refine high-precision tracking performances of agents, a graph-based distributed learning control (DLC) law is proposed, for which a new bounded-initialization, bounded-updating (BIBU) stability property is explored under any bounded initial conditions. Moreover, a class of heterogeneous-to-homogeneous transformation methods is introduced, together with presenting feasible gain design conditions, for DLC. It is shown that with the designed DLC law, not only can the effect of the agents' heterogeneous dynamics in performing DLC be well overcome, but also the BIBU stability and the robust cooperative output tracking of agents can be simultaneously accomplished. A simulation test is also implemented to verify the validity of our developed DLC results for heterogeneous vehicle networks. [ABSTRACT FROM AUTHOR]

Academic collaboration recommendation (ACR) can help researchers find potential partners for research and thus promote academic innovation. Recent works mostly use graph learning-based methods to explore various ways of combining node information with topology, which consists of multiple steps, including network construction, node feature extraction, network representation learning and link prediction. One limitation is that they only conduct research on co-authorship networks and ignore citation relationship between publications. Besides, they tend to use attributes from a single dimension of researchers and do not take attributes of researchers from multiple dimensions into consideration at the same time. To address the above issues, we present the multi-dimensional attributes enhanced heterogeneous (MAH) network representation learning method, which constructs heterogeneous networks with both co-authorship and citation information and makes use of multi-dimensional attributes. Three research questions are addressed in this work: (RQ1) Is our proposed method effective on academic collaboration recommendation compared with existing state-of-the-art methods? (RQ2) Does incorporating citation information into co-authorship network help improve the performance of academic collaboration recommendation? (RQ3) How does fusing multi-dimensional attributes affect the performance of academic collaboration recommendation? A publicly available real-world data set is used in our experiments. The superior performance of MAH compared with baseline methods demonstrates that the proposed multi-dimensional feature-based researcher profile can enrich node information in academic network and effective researcher representations can be learned by applying graph representation learning methods on the network. [ABSTRACT FROM AUTHOR]

Drug–target interaction (DTI) identification is a complex process that is time-consuming, costly and frequently inefficient, with a low success rate, especially with wet-experimental methods. The prediction of DTI by calculational methods is an effective way to solve this problem. However, most existing methods regard drug–target pairs with unknown interaction relationship as negative samples, that the false negative samples will affect the AUC and AUPR evaluation, leading to performance misjudgment. Therefore, in this paper, a new DTI prediction method, DTI-HAN, is proposed to overcome the shortcoming and further improve the predictive performance. In the drug and target feature representation learning stage, this method constructs a drug–target heterogeneous network based on similarity and interaction relationship, and establishes meta-path, node-level and semantic-level bi-attention mechanism. To avoid introducing false negative examples, an improved loss function based only on known edges is proposed. In the DTI prediction stage, feature projection and fuzzy theory are introduced, and membership distribution function is estimated only depended on positive samples. Compared with the DTI prediction methods, DTI-GAT, DTI-GCN and DTI-GraphSAGE, as well as BLM, DTHybrid, SCMLKNN and FPSC-DTI, the experimental results on Enzyme, GPCR, Ion Channel and Nuclear Receptor 4 datasets showed that the DTI-HAN method can greatly improve the AUC and AUPR values on at least 3 datasets to each method. Furthermore, the novel top 100-pair of DTIs prediction were verified by KEGG, DrugBank, ChEMBL and SuperTarget databases, and obtained 21, 48, 61 and 28 validation records, respectively. The top-5 remaining unverified DTIs were performed molecular docking with AutoDock Vina, and the results showed that these drugs and targets have good binding properties. The code and data are available at https://github.com/Yu123456/DTI-HAN. • A new DTI prediction framework (DTI-HAN) was proposed. • The DTI-HAN introduced many effective techniques. • The DTI-HAN improved the loss function. • Experimental results showed that the DTI-HAN improved performance. [ABSTRACT FROM AUTHOR]

Influence maximization (IM) has drawn significant attention in recent years. Most existing IM methods primarily focus on homogeneous networks, and do not take into account the heterogeneity and the attributes of different types of nodes in heterogeneous networks. However, heterogeneous networks are ubiquitous in real world, encompassing rich semantics and complex structural information. Additionally, the clustering characteristics inherent in a network have a critical and substantial impact on the process of information diffusion, which is often overlooked in IM models designed for heterogeneous networks. To address the challenges posed by the heterogeneity and clustering structure in heterogeneous networks, we propose a novel deep learning framework based on a self-supervised clustered heterogeneous graph transformer for IM in heterogeneous networks, which we have named SCHGT-IM. SCHGT-IM aggregates the heterogeneity and clustering information in heterogeneous networks and incorporates a clustered cascade (CC) model as an information diffusion model to enhance the realism of simulations. We evaluate the performance of SCHGT-IM in comparison with that of state-of-the-art IM models using three academic heterogeneous networks extracted from the DBLP dataset. The experimental results on influence spread demonstrate that SCHGT-IM is superior to fourteen state-of-the-art algorithms and is highly effective in selecting influential seed nodes of different types from heterogeneous networks. • A self-supervised clustered HGT method SCHGT-IM for IM on heterogeneous network is proposed. • SCHGT-IM integrates cluster information from heterogeneous networks. • SCHGT-IM includes information diffusion model, named the clustered cascade model. • SCHGT-IM outperforms fourteen state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Heterogeneous network link prediction is a hot topic in the analysis of networks. It aims to predict missing links in the network by utilizing the rich semantic information present in the heterogeneous network, thereby enhancing the effectiveness of relevant data mining tasks. Existing heterogeneous network link prediction methods utilize meta-paths or meta-graphs to extract semantic information, heavily relying on the priori knowledge. This paper proposes a heterogeneous network link prediction based on network schema and cross-neighborhood attention method (HNLP-NSCA). The heterogeneous node features are projected into a shared latent vector space using fully connected layers. To resolve the issue of prior knowledge dependence on meta-path, the semantic information is extracted by using network schema structures uniquely in heterogeneous networks. Node features are extracted based on the relevant network schema instances, avoiding the problem of meta-path selection. The neighborhood interaction information of input node pairs is sensed via cross-neighborhood attention, strengthening the nonlinear mapping capability of the link prediction. The resulting cross-neighborhood interaction vectors are combined with the node feature vectors and fed into a multilayer perceptron for link prediction. Experimental results on four real-world datasets demonstrate that the proposed HNLP-NSCA mothed outperforms the baseline models. [ABSTRACT FROM AUTHOR]