Graph conjoint attention (CAT) network is one of the best graph convolutional networks (GCNs) frameworks,
which uses a weighting mechanism to identify important neighbor nodes. However, this weighting mechanism is
learned based on static information, which means it is susceptible to noisy nodes and edges, resulting in significant
limitations. In this paper, a method is proposed to obtain context dynamically based on random walk, which allows
the context-based weighting mechanism to better avoid noise interference. Furthermore, the proposed context-based
weighting mechanism is combined with the node content-based weighting mechanism of the graph attention (GAT)
network to form a model based on a mixed weighting mechanism. The model is named as the context-based and
content-based graph convolutional network (CCGCN). CCGCN can better discover important neighbors, eliminate
noise edges, and learn node embedding by message passing. Experiments show that CCGCN achieves state-of-the-
art performance on node classification tasks in multiple datasets.

Membership inference attacks on machine learning models have drawn significant attention. While current  research primarily utilizes shadow modeling techniques, which require knowledge of the target model and training  data, practical scenarios involve black-box access to the target model with no available information. Limited  training data further complicate the implementation of these attacks. In this paper, we experimentally compare  common data enhancement schemes and propose a data synthesis framework based on the variational autoencoder  generative adversarial network (VAE-GAN) to extend the training data for shadow models. Meanwhile, this paper  proposes a shadow model training algorithm based on adversarial training to improve the shadow model's ability to  mimic the predicted behavior of the target model when the target model's information is unknown. By conducting  attack experiments on different models under the black-box access setting, this paper verifies the effectiveness of the  VAE-GAN-based data synthesis framework for improving the accuracy of membership inference attack.  Furthermore, we verify that the shadow model, trained by using the adversarial training approach, effectively  improves the degree of mimicking the predicted behavior of the target model. Compared with existing research  methods, the method proposed in this paper achieves a 2% improvement in attack accuracy and delivers better  attack performance.

To solve the privacy leakage problem of truck trajectories in intelligent logistics, this paper proposes a Quadtree-based Personalized Joint location Perturbation (QPJLP) algorithm using location generalization and local differential privacy techniques. Firstly, a flexible position encoding mechanism based on the spatial quadtree indexing is designed, and the length of the encoding can be adjusted freely according to data availability. Secondly, to meet the privacy needs of different locations of users, location categories are introduced to classify locations as sensitive and ordinary locations. Finally, the truck invokes the corresponding mechanism in the QPJLP algorithm to locally perturb the code according to the location category, allowing the protection of non-sensitive locations to be reduced without weakening the protection of sensitive locations, thereby improving data availability. Simulation experiments demonstrate that the proposed algorithm effectively meets the personalized trajectory privacy requirements while also exhibiting good performance in trajectory proportion estimation and Top-K classification.

In this paper, a novel superjunction 4H-silicon carbide (4H-SiC) trench-gate insulated-gate bipolar transistor (IGBT) featuring an integrated clamping PN diode between the P-shield and emitter (TSD-IGBT) is designed and theoretically studied. The heavily doping superjunction layer contributes to a low specific on-resistance, excellent electric field distribution, and quasi-unipolar drift current. The anode of the clamping diode is in floating contact with the P-shield. In the on-state, the potential of the P-shield is raised to the turn-on voltage of the clamping diode, which prevents the hole extraction below the N-type carrier storage layer (NCSL). Additionally, during the turn-off transient, once the clamping diode is turned on, it also promotes an additional hole extraction path. Furthermore, the potential dropped at the semiconductor near the trench-gate oxide is effectively reduced in the off-state.

In this work, β-Ga₂O₃ thin films were grown on SiO₂ substrate by atomic layer deposition (ALD) and annealed in N₂ atmosphere to enhance the crystallization quality of the thin films, which were verified from X-rays diffraction (XRD). Based on the grown β-Ga₂O₃ thin films, vertical metal-semiconductor-metal (MSM) interdigital photodetectors (PDs) were fabricated and investigated. The PDs have an ultralow dark current of 1.92 pA, ultra-high photo-to-dark current ratio (PDCR) of 1.7×10⁶, and ultra-high detectivity of 4.25×10¹⁴ Jones at a bias voltage of 10 V under 254 nm deep ultraviolet (DUV). Compared with the horizontal MSM PDs under the same process, the PDCR and detectivity of the fabricated vertical PDs are increased by 1 000 times and 100 times, respectively. In addition, the vertical PDs possess a high responsivity of 34.24 A/W and an external quantμm efficiency of 1.67×10⁴%, and also exhibit robustness and repeatability, which indicate excellent performance. Then the effects of electrode size and external irradiation conditions on the performance of the vertical PDs continued to be investigated.

An artificial rabbit optimization algorithm based on chaotic mapping and Levy flight improvement is proposed, which has the advantages of good initial population quality and fast convergence compared with the traditional artificial rabbit optimization algorithm, called CLARO. CLARO’s improvement method starts from three aspects: to optimize the quality of the initial population of the algorithm a chaotic mapping is brought in to initialize the population; to avoid the algorithm from falling into local optimum Levy flight is added in the exploration phase and the threshold of energy factor A is optimized to better balance exploration and exploitation. The efficiency of CLARO is tested on a set of 23 benchmark function sets by comparing it with ARO and different meta-heuristics algorithms. At last, the comparison experiments conclude that all three improvement strategies enhance the performance of ARO to some extent, with Levy flight providing the most significant improvement in ARO performance. The experimental results showed that CLARO has better results and faster convergence compared to other algorithms, while successfully addressing the drawbacks of ARO and being able to face more challenging problems.

In this paper, a novel trench gate gallium nitride insulated gate bipolar transistor (GaN IGBT), in which the collector is divided into multiple regions to control the hole injection efficiency, is designed and theoretically studied. The incorporation of a P+/P- multi-region alternating structure in the collector region mitigates hole injection within the collector region. When the device is in forward conduction, the conductivity modulation effect results in a reduced storage of carriers in the drift region. As a result, the number of carriers requiring extraction during device turn-off is minimized, leading to faster turn-off speed. The results illustrate that the GaN IGBT with controlled hole injection efficiency (CEH GaN IGBT) exhibits markedly enhanced performance compared to conventional GaN IGBT, showing a remarkable 42.2% reduction in turn-off time and a notable 28.5% decrease in turn-off loss.

In this paper, the online power control and rate adaptation for a wireless communication system with energy harvesting are investigated, in which soft decision decoding is adopted by the receiver. To efficiently utilize the harvested energy and maximize the average actual information transmission rate, transmit power, modulation order and code rate are jointly optimized. The Lyapunov framework is utilized to transform the long-term optimization problem into an optimization problem per time slot. Since there is no theoretical formula for the error rate of soft decision decoding, the optimization problem cannot be analytically solved. A table to find the optimal modulation order and code rate under the different values of signal-to-noise ratio is built first, and then a numeric algorithm to find the solution to the optimization problem is given. The feasibility and performance of the proposed algorithm are demonstrated by simulation. The simulation results show that compared with the algorithms to maximize the theoretic channel capacity, the proposed algorithm can achieve a higher actual transmission rate.

As a fact, most constructed knowledge graphs are far from complete no matter its size. This incompleteness will cause negative influence on the applications based on knowledge graphs. As an important method for knowledge graph complementation, link prediction has become a hot research topic in recent years. In this paper, a performance enhancement scheme for link prediction models based on the idea of semi-supervised learning and model soup is proposed, which effectively improves the model performance on several mainstream link prediction models with small changes to their architecture. This novel scheme consists of two main parts: (1) predicting potential fact triples in the graph with semi-supervised learning strategies, (2) creativily combining semi-supervised learning and model soup to further improve the final model performance without adding significant computational overhead. We experimentally validate the effectiveness of the scheme for a variety of link prediction models, especially on the dataset with dense relationships. In terms of CompGCN, the model with the best overall performance among the tested models improves its Hits@1 metric by 14.7% on the FB15K-237 dataset and 7.8% on the WN18RR dataset after using the enhancement scheme. Meanwhile, we observe that the semi-supervised learning strategy in the augmentation scheme has significant improvement for multi-class link prediction models, and the performance improvement brought by the introduction of the model soup is related to the specific tested models, because performance of some models are improved while others remained largely unaffected.

A new procedure of distributed self-control coverage for monitoring the dynamic targets with mobile sensor network is proposed. A special model is given for maintaining the nodes bi-connectivity and optimizing the coverage of the moving targets. The model consists of two parts, the virtual force model is proposed for motion control and the whale optimization algorithm is improved to further optimize the node positions and to reach the steady state quickly. The virtual resultant force stretches the network toward the uncovered targets by its multi-target attractive force, and maintains the network connectivity by its attractive force while network stretching, and avoids node collisions by its repulsive force while nodes moving. The operating mechanism of multi-target attractive force and other forces is also profoundly anatomized. The adjustment criteria for the model in different application scenarios are also given. Finally, the comparisons are shown to be significant advantages over other similar kinds.

In the classification problem, deep kernel extreme learning machine (DKELM) has the characteristics of efficient
processing and superior performance, but its parameters optimization is difficult. To improve the classification
accuracy of DKELM, a DKELM algorithm optimized by the improved sparrow search algorithm (ISSA), named as
ISSA-DKELM, is proposed in this paper. Aiming at the parameter selection problem of DKELM, the DKELM
classifier is constructed by using the optimal parameters obtained by ISSA optimization. In order to make up for the
shortcomings of the basic sparrow search algorithm (SSA), the chaotic transformation is first applied to initialize the
sparrow position. Then, the position of the discoverer sparrow population is dynamically adjusted. A learning
operator in the teaching-learning-based algorithm is fused to improve the position update operation of the joiners.
Finally, the Gaussian mutation strategy is added in the later iteration of the algorithm to make the sparrow jump out
of local optimum. The experimental results show that the proposed DKELM classifier is feasible and effective, and
compared with other classification algorithms,the proposed DKELM algorithm aciheves better test accuracy.

This article presents the design and performance of a single-pole double-throw (SPDT) switch operating in 50–110 GHz. The switch is fabricated in a 100-nm GaN high-electron-mobility transistors(HEMT) technology. To realize high-power capability, the dimensions of GaN HEMTs are selected by simulation verification. To enhance the isolation, an improved structure of shunt HEMT with two ground holes is employed. To extend the operation bandwidth, the SPDT switch with multi section resonant units is proposed and analyzed. To verify the SPDT switch design, a prototype operating in 50–110 GHz is fabricated. The measured results show that the fabricated SPDT switch monolithic microwave integrated circuit (MMIC) achieves an input 1 dB compression point (P_1dB) of 38 dBm at 94 GHz, and an isolation within the range of 33 dB to 54 dB in 50–110 GHz. The insertion loss of the switch is less than 2.1 dB, while the voltage standing wave ratios (VSWR) of the input port and output port are both less than 1.8 in the operation bandwidth. Based on the measured results, the presented SPDT switch MMIC demonstrates high power capability and high isolation compared with other reported millimeter-wave SPDT MMIC designs.

The continuous phase modulation (CPM) technique is widely used in range telemetry due to its high spectral
efficiency and power efficiency. However, the demodulation performance of the traditional maximum likelihood
sequence detection (MLSD) algorithm significantly deteriorates in non-ideal synchronization or fading channels. To
address this issue, this work proposes a convolutional neural network (CNN) called the cascade parallel crossing
network (CPCNet) to enhance the robustness of CPM signals demodulation. The CPCNet model employs a multiple
parallel structure and feature fusion to extract richer features from CPM signals. This approach constructs feature
maps at different levels, resulting in a more comprehensive training of the model and improved demodulation
performance. Simulation results show that under Gaussian channel, the proposed CPCNet achieves the same bit
error rate (BER) performance as MLSD method when there is no timing error, but with 1/4 symbol period timing
error, the proposed method has 2 dB demodulation gain compared with CNN and convolutional long short-term
memory deep neural network (CLDNN). In addition, under Rayleigh channel, the BER of the proposed method is
reduced by 5% -87% compared to that of MLSD in the wide signal-to-noise ratio (SNR) region.