Drug-target binding affinity prediction is critical to drug design. Some existing computational methods rely on single-scale data and cannot fully integrate the rich information of multi-scale data, such as molecular structures and network information. In this paper, we propose the MBC-DTA model, which effectively integrates multi-scale data, and models the complex interactions between atoms and amino acids. We introduce GCN and GAT, which effectively extract the feature representation of molecular structure scale and network scale. Afterwards, the features obtained from the molecular structure scale are fed into a bilinear attention network, which captures the intricate interaction information between drug-target pairs. Additionally, a cross-scale graph contrastive learning strategy is applied, optimizing the feature representations across different scales. Extensive experimental results on two benchmark datasets demonstrate that the MBC-DTA model outperforms existing state-of-the-art methods.

Drug-target interaction (DTI) prediction is a critical step in drug discovery. Deep learning has shown great potential in DTI prediction. In recent years, many sequence-based DTI prediction methods have been proposed. However, the current methods do not fully represent drugs and proteins and ignore the local and global features of these molecules. In response to these challenges, we propose a sequence-based CNN and Transformer collaborative prediction method (SCTDTI) for drug-target interaction. We train and evaluate our proposed approach on two public drug-target datasets, and experimental results show that SCTDTI improves DTI prediction performance compared to state-of-the-art baselines.

Query embedding (QE) is designed to embed entities and first-order logic (FOL) queries in low-dimensional spaces, it has demonstrated considerable effectiveness in multi-hop reasoning over knowledge graphs. Recently, the practice of embedding entities and queries using geometric shapes has emerged as a promising approach, given the natural ability of these shapes to represent query answer sets and the logical relationships between them. However, existing geometry-based models, such as those employing point and box embeddings, cannot handle logical negation operations. Additionally, these models typically focus only on entities and relations, overlooking the rich semantic information available in knowledge graphs. To address these limitations, we propose the Type-aware Enhanced Cylinder Embedding (TECE) model. This model leverages three-dimensional geometric representations, integrating entity relationship type information. TECE covers a spectrum of essential First-Order Logic (FOL) operations, such as conjunctive, disjunctive, and negative. TECE improves the representation of entities and relationships in queries by incorporating semantic information. Moreover, it strengthens the model’s ability in generalization, along with deductive and inductive reasoning. Our experiment results demonstrate that TECE achieves significantly superior performance compared with existing SOTA methods on standard datasets.

Recently, Multimodal Knowledge Graphs (MKGs) with visual and textual factual knowledge have been widely used in tasks such as knowledge question answering, recommender systems, and entity disambiguation. Since most of the current MKGs still have defects, a multimodal knowledge graph completion technology is proposed, and multimodal relation extraction (MRE) is one of the basic processes. However, visual objects with high object classification scores are usually selected in previous tasks, which may result in the addition of noise from objects that are either irrelevant or redundant, which can adversely affect multimodal relationship extraction. For this reason, in this paper, we propose a Relation Extraction with Knowledge-enhanced Prompt-tuning modal on multimodal knowledge graph (REKP) to address these issues. Specifically, we inject potential knowledge from relational labels into the prompt construction of answer words and optimize their representation with structured constraints. A Transformer architecture with cross-modal attention is then used to fuse the visual and textual representations. We conduct extensive experiments to verify that our REKP model can achieve SOTA performance on the MNRE dataset with multimodal relational extraction.

With the development of 6G, millimeter wave communication has received extensive attention. Due to the characteristics of wireless transmission, information secrecy transmission is facing significant challenges. This paper uses the physical layer security (PLS) to explore the information secrecy transmission. Specifically, we use Intelligent Reflecting Surface (IRS) to control the wireless propagation environment and improve the secrecy rate of millimeter wave communication. The active beamforming matrix of the base station and the passive beamforming matrix of the IRS are optimized to achieve the maximum secrecy rate. We deduce the closed form solution of active beamforming and the approximate optimal solution of passive beamforming. An alternating optimization (AO) algorithm is applied to solve the non-convex optimization problem. Simulation results verify the convergence and effectiveness of the algorithm, which can obtain nearly twice the secrecy rate gain of the benchmark algorithm.

Unmanned aerial vehicles (UAVs) have been widely used in wireless communication network for its high flexibility and broad coverage. However, due to the wireless broadcast and high power consumption features of UAV networks, physical layer secrecy (PLS), spectrum efficiency and energy supply are of major importance. In this paper, we propose a novel untrusted simultaneous wireless information and power transfer (SWIPT) UAV relaying network in which cooperative jamming is utilized to enhance secrecy performance. We take advantage of nonorthogonal multiple access (NOMA) technique to improve the spectrum efficiency. For energy supply, the UAV relay harvests energy from source and jammer node using power splitting (PS) scheme as well as amplifies and forwards (AF) the signal. The closed expressions of connection outage probability (COP) and secrecy outage probability (SOP) are derived over Nakagami-m fading channel. Simulation results demonstrate that the communication network security has been improved compared with orthogonal frequency division multiple access (OFDMA) network. Finally, minimum COP and SOP value can be achieved with appropriate parameters.

In the background of ultra-dense network (UDN), with the increasingly densification of network structure, the distance between base stations becomes closer, and one user may be in the service range of multiple small base stations, thus forming a user-centered virtual cell system. In this system, with more and more unlimited devices accessed to the network, spectrum resources are becoming more and more tense. Compared with orthogonal multiple access (OMA), non-orthogonal multiple access (NOMA) can make better use of spectrum resources to meet the access requests of more access devices. In recent years, more and more attentions are drawn to information security issues, so it is important to use physical layer security (PLS) technology to ensure the safe access of users in the presence of eavesdropping nodes. This paper discusses the user access issue in UDN considering PLS and NOMA, and proposes a non-cooperative game theory method to maximize sum of the User's communication rate in the system through multi-round dynamic games. Through simulation analysis, we proved the effectiveness of our proposed method.

Non-used clinical information has negative implications on healthcare quality. Clinicians pay priority attention to clinical information relevant to their specialties during routine clinical practices but may be insensitive or less concerned about information showing disease risks beyond their specialties, resulting in delayed and missed diagnoses or improper management. In this study, we introduced an electronic health record (EHR)-oriented knowledge graph system to efficiently utilize non-used information buried in EHRs. EHR data were transformed into a semantic patient-centralized information model under the ontology structure of a knowledge graph. The knowledge graph then creates an EHR data trajectory and performs reasoning through semantic rules to identify important clinical findings within EHR data. A graphical reasoning pathway illustrates the reasoning footage and explains the clinical significance for clinicians to better understand the neglected information. An application study was performed to evaluate unconsidered chronic kidney disease (CKD) reminding for non-nephrology clinicians to identify important neglected information. The study covered 71,679 patients in non-nephrology departments. The system identified 2,774 patients meeting CKD diagnosis criteria and 10,377 patients requiring high attention. A follow-up study of 5,439 patients showed that 82.1% of patients who met the diagnosis criteria and 61.4% of patients requiring high attention were confirmed to be CKD positive during follow-up research. The application demonstrated that the proposed approach is feasible and effective in clinical information utilization. Additionally, it's valuable as an explainable artificial intelligence to provide interpretable recommendations for specialist physicians to understand the importance of non-used data and make comprehensive decisions.

In this paper, a novel strategy of relay selection and cooperative jammer beamforming is proposed. The proposed scheme selects one node from the intermediate nodes as relay and the rest nodes as friendly jammers. The relay operates in amplify-and-forward (AF) strategy. Jammer weights are derived to null the jamming signals at the destination and relay node and maximize the jamming signal at the eavesdropper. Furthermore, a closed-form optimal solution of power allocation between the selected relay and cooperative jammers is derived. Numerical simulation results show that the proposed scheme can outperform the conventional schemes at the same power consumption.

In this paper, we investigate the security of cellular networks using cooperative jamming with imperfect wiretap channel status information (CSI). Firstly, the CSI of the eavesdropper is considered imperfect and modeled as a sphere with a certain center and a radius which is the estimated channel of eavesdropper, and then the optimization of the worst-case secrecy rate is given. Secondly, using semidefinite relaxation (SDR) and a search method, the SDR-based scheme is proposed to maximize the secrecy rate. To reduce the complexity, a second scheme to optimize the ratio between interference to the eavesdropper and to the legitimate user, which is transmitted by jammers, is introduced. Finally, the numerical results demonstrate the excellent performance of the two strategies, and the performance of the low-complexity scheme is very close to that of the SDR-based scheme.

This work studies the security enhancement and social relationship model in heterogeneous D2D and cellular network with an adaptive jamming. Different from traditional physical layer securities that optimize secrecy capacity, we investigate strategies based on reduction of compromised secrecy region (CSR). Specifically, we firstly format the outage probability while taking fading channel effects into consideration and we build a novel social relationship model evaluated by social interactions and physical secrecy outage probability. Then three strategies for adaptive jamming are proposed to reduce CSR at various levels of channel states in the presence of joint cellular user and adaptive jammer beam-forming. Finally, numerical approximation and results validate the proposed CSR optimization strategies for joint artificial noise from cellular user and adaptive jammer and our scheme could reduce CSR efficiently.

In this paper, we investigate the Physical Layer Security (PLS) of a multiple friendly jammers and multiple users wireless system in Device-to-Device (D2D) communications underlaying cellular networks with an eavesdropper. The aim is to maximize the increase of secrecy capacity of the entire system through optimal power allocation and jamming matching under various practical constraints. Firstly, the total increase secrecy capacity of D2D pairs with the help of jamming is derived, then we obtain optimal jamming power for each D2D pair and formulate the D2D pairs and jammers matching problem in the weighted bipartite graph via designing the Kuhn-Munkres (KM) algorithm. Finally, numerical results demonstrate that our scheme could greatly improve the secrecy performance of heterogeneous D2D and cellular networks.

In this paper, we study the secret-key capacity of the secure cooperative network using the collaborative amplify-andforward (AF) relays to form a beamforming system through the physical layer. The closed-form expression of secret-key capacity is firstly given to prove the the secret-key capacity is not only achievable but can be designed and optimized by beamforming vector formed by AF relays. Furthermore, three beamforming solutions are proposed to maximize the secret-key capacity under the total relay power constraint. The first solution, maximum secret-key capacity (MSKC) beamforming solution, is aimed towards two-level optimization problems and performed by using the semidefinite relaxation (SDR) technique. This solution is the closest to the optimal solution of original problem, but its complexity is very high because of the SDPs. To decrease the complexity, the signals at all eavesdroppers are forced to be zero, producing the second solution named zero-forcing (ZF) beamforming solution. However, the ZF beamforming solution does not work when the number of eavesdroppers is larger than that of relays. The third solution, lower bound maximum secretkey capacity (LB-MSKC) beamforming solution, is designed to make up the loss. It simplifies the original problem to a one-level optimization problem by relaxing the eavesdroppers, and it can still work well when the number of eavesdroppers is larger than that of relays. Simulation results are presented to illustrate the proposed solutions.

This paper exploits physical layer network coding (PNC) and friendly jamming to improve their physical layer security in wireless two-hop cooperative communications, consisting of one source-destination pair with the help of multiple intermediate nodes in the presence of one eavesdropper. By sending a jamming signal carrying a random binary message from the selected jammer and utilizing the PNC at the selected relay node, the system can avoid the disadvantage of the friendly jamming to the source-relay channel and do good to the relay-destination channel, thereby achieving better secrecy rate. Assuming global channel state information available and memoryless adversaries, we seek to minimize the secrecy outage probability with the optimal relay and jammer selection. Numerical simulation results show that our schemes outperform the conventional approaches in wireless cooperative communications.

In this paper, we investigate physical layer network coding (PNC) and destination assisted cooperative jamming (DACJ) for physical layer security in wireless sensor networks, in which there is one source, one destination, a cluster of intermediate nodes, and multiple eavesdroppers. Under the PNC protocol, the considered two-hop wireless sensor network implements a complete transmission process in two phases. In the first phase, through sending a jamming signal from the destination and exploiting the PNC at the relay, the relay decodes the exclusive-OR (XOR) performed form of the source and the jamming message. Therefore, the jamming signal can degrade the wire-tap channels without hampering the legitimate channel. In the second phase, the relay transmits the re-encoded message to the destination while eavesdroppers are out of work as they cannot extract information from the signal. Thus, the proposed design can significantly improve the performance of secure wireless communications. Meanwhile, the proposed schemes select one optimal node from the intermediate nodes and give an optimal solution of power allocation to maximize secrecy capacity. Numerical simulation results show that the proposed schemes have a better and more stable secrecy performance than the conventional schemes at the same power consumption.

In this paper, we investigate the physical layer security scheme in heterogeneous Device-to-Device (D2D) and cellular networks. More specifically, we aim to optimize the secrecy capacity of D2D users in a single cell where the D2D users share downlink resource with cellular users. We assume that base station is equipped with multiple antennas while other nodes are equipped with single antenna, and the eavesdropper is intending to wiretap the information of D2D user. Base station transmits artificial noise as the jamming-aided signal to degrade the wiretap channel such that the security capacity of D2D user could be improved. First, we design the precoding matrix of artificial noise to make sure that the wiretap channel would be degraded while D2D link and cellular link are not influenced. Second, the precoding matrix of desired information signal of cellular link is designed in order to satisfy the quality demand of cellular link. In this part, we propose three schemes according to different criteria. Finally, the optimal power allocation algorithm is provided. Simulation results demonstrate that our scheme could efficiently improve the secrecy capacity of D2D user while the quality demand of cellular user is satisfied.

In underlay D2D communications, cellular users share resource with D2D users, which may cause severe interference. When cellular cells have light loads, overlay D2D communications can be applied to avoid interference. In this paper, we adopted overlay D2D mode under which D2D resource is orthogonal to cellular user resource. We proposed two location-based D2D resource allocation algorithms for V2V (vehicle-to-vehicle) broadcast service, separately Location-based Centralized Sched-uling Algorithm (LB-CSA) and Location-based Distributed Scheduling Algorithm (LB-DSA). Further, we researched trans-mission accuracy, time delay and resource utilization performances of the algorithms. Results show that LB-DSA has relatively lower demand on communication facilities, while LB-CSA performs slightly better in performances of time delay, transmission accuracy and resource reuse. Both of the two algorithms can realize resource spatial reuse and improve resource utilization efficiency, meanwhile controlling packet error rate at an acceptable level.

Vehicle-to-Vehicle (V2V) Safety Communication is committed to reduce traffic accidents by information exchange between vehicles. This paper studies the V2V safety communication based on cellular systems, especially LTE, where vehicles send Cooperative Awareness Messages (CAM) periodically to Base Stations (BSs) and the BSs transmit the CAMs to target vehicles through appropriate strategies. For the case of vehicle to multi-vehicle communication(usually cross cell), Multimedia Broadcast multicast service Single Frequency Network(MBSFN) can be adopted to achieve better performance compared with unicast because every message is only transmitted once reaching all target vehicles which reduce network load. A novel MBSFN scheme is designed in this paper. Simulation results show that our proposed MBSFN scheme can support more cars than the existing scheme under the same latency and QoS constraints.

In this study, a two‐stage decode‐and‐forward cooperative network is investigated consisting of a source, a corresponding destination, an eavesdropper and several intermediate nodes. In this study, the authors present an analysis of overall secrecy rate considering both distributed relay selection and secure beamforming problems. The achievable rate constraint is newly included into the system model. This modelling framework offers a more reliable approximation of the practical wireless channel. The relay selection is formulated as a coalitional game with transferable utility, which decreases the computation complexity in solving the distributed relay selection problem. A new ‘Max–Pareto order’ is constructed, which not only considers the player value, but also reflects the dominated weight of coalition value. Moreover, a distributed merge‐and‐split coalition formation algorithm is presented in this study. This algorithm achieves the system performance close to the theoretical upper limit, but it requires much less computation consumption.

A conventional inverse synthetic aperture radar image is a 2-D range-Doppler projection of a target and does not provide 3-D information. Three-dimensional imaging using an interferometric technique cannot separate scatterers that have been projected onto the same range-Doppler unit. Multiple-input–multiple-output (MIMO) radar, however, in addition to having a wide virtual aperture and a high cross-range resolution, could also obtain a target's 3-D image in one snapshot. We discuss in this paper the use of time-domain information to improve MIMO radar's imaging quality. A 3-D image alignment algorithm and a rotation vector estimation method are discussed. Simulation results show that image SNR is improved and cross-range sidelobes are mitigated.

Gibbs sampler, a typical Markov chain Monte Carlo (MCMC) method that approximately solves the Bayesian problem by simple numerical computation in a completely different paradigm was previously employed for the Bayesian detection in synchronous CDMA system. To perform the Bayesian detection for the asynchronous uplink CDMA system with unknown multiuser interference and multipath fading, the Gibbs sampler combined with the linear group-blind decorrelator is proposed as a novel Bayesian multiuser detection technique in this paper. Furthermore, in the study of the effect of channel estimation error on the performance of the proposed detector, we also present an iterative Bayesian multiuser detector where more accurate parameter estimation is achieved to improve the detection performance. Simulation results verify the effectiveness of the proposed detectors. The proposed detection techniques have the advantages of low complexity, high performance and wide applications.