Search

Blockchain is gaining popularity as a technology that provides secure data sharing and management for the Internet of vehicles (IoV). The current research on cross-chaining between blockchains is still inefficient, and how to perform efficient cross-chain data communication has not been well studied. This paper studies the cross-chain protocol in the IoV environment, and designs a lightning-c cross-chain protocol based on the lightning network. The protocol consists of three steps. The user opens the cross-chain channel through election of nodes, and conducts transactions in the cross-chain channel, then the cross-chain channel is closed and the transaction is broadcasted to the blockchain. Our proposed approach enables efficient interoperability between heterogeneous blockchains. Compared with the traditional cross-chain protocol BTCRelay, it is proved that the lightning-c cross-chain mechanism can greatly improve the throughput of cross-chain transactions. The experimental results show that the method proposed in this paper is more efficient.

This study investigates the potential of Particle Swarm Optimization (PSO)-based Neural Network (NN) training to enhance the efficacy of English language instruction. Recognizing English as a global language vital for international communication and economic interaction, effective language training is imperative. Leveraging PSO as a guiding mechanism for NN training presents a novel approach to refine instructional strategies. This study critically examines existing literature and identifies shortcomings in conventional algorithms employed in English teaching methodologies. Subsequently, a sophisticated algorithmic framework integrating PSO with NN is proposed to address these deficiencies and augment instructional outcomes. The adaptability of this methodology to conventional teaching models in English language education is explored. Experimentation and simulation validate the effectiveness of this innovative approach, illustrating its potential to revolutionize English education by optimizing learning outcomes. The findings underscore the significance of PSO-driven NN training in enhancing teaching effectiveness, paving the way for advancing English language education methodologies.

In recent years, human beings have paid more and more attention to the exploration of the underwater world. As an important part of underwater resources, fish can be detected by using the fish image data collected by underwater imaging systems, which can help us better understand fish species richness and assess fish populations. In this paper, we proposed a fish target detection algorithm YOLOv5-fish for underwater blurred scenes. For underwater blurred scenes, the algorithm first uses the auto-MSRCR algorithm to enhance the acquired low-quality underwater blurred image data and obtains the enhanced fish images as the dataset for model training. Then the YOLOv5s algorithm is improved through the following methods. First, replacing the original activation function with Meta-ACON to realize the model autonomously control the nonlinearity degree of the activation function; Second, adding the Shuffle Attention mechanism to enhance the model’s attention to the detection object; Third, introducing RepVGG structure to the backbone network to accelerate the model’s inference speed. The experimental results show that the improved YOLOv5-fish algorithm achieves an mAP of 97.6% and a detection speed of 84 FPS, which can achieve accurate and fast detection for fish targets in underwater blurred scenes.

In this paper, a dual-band dual-polarized antenna array based on magneto-electric (ME) dipoles is proposed, which is simply excited by two orthogonal $L$ -shaped strips. The antenna element has a compact size of $0.45\,\,\lambda \times 0.45\,\,\lambda \times 0.12\,\,\lambda $ at 34 GHz. By adding inductive blind vias at the four corners of the ground plane, better impedance matching, larger front-to-back ratio (FBR) and higher gain at the low frequency band are achieved. Due to the resonances of the magnetic dipole and the electric dipole, large bandwidths of 24.4-28.9 GHz and 34.2-43.4 GHz are obtained for the ±45° polarized antennas, covering the n258 and n260 bands for 5G communications. At the same time, a stable radiation pattern is retained, with a high gain of above 5 dBi over the operating band for both polarizations. With the $1\times4$ array, the beam scanning range from −60° to +60° is retained at 26.5 GHz, whereas it is from −53° to +53° at 39 GHz, making it competitive for implementations in mobile handsets.

Cross-project defect prediction (CPDP) aims to build a prediction model on existing source projects and predict the labels of target project. The data distribution difference between different projects makes CPDP very challenging. Besides, most existing CPDP methods usually require sufficient and labeled data. However, acquiring lots of labeled data for a new project is difficult while obtaining the unlabeled data is relatively easy. A desirable approach is building a prediction model on unlabeled data and labeled data. CPDP in this scenario is called cross-project semi-supervised defect prediction (CSDP). Recently, generative adversarial networks have achieved impressive results with these strong ability of learning data distribution and discriminative representation. For effectively learning the discriminative features of data from different projects, we propose a Discriminative Adversarial Feature Learning (DAFL) approach for CSDP. DAFL consists of feature transformer and project discriminator, which compete with each other. A feature transformer tries to generate feature representation, which learns the discriminant information and preserves intrinsic structure inferred from both labeled and unlabeled data. A project discriminator tries to discriminate source and target instances on the generated representation. Experiments on 16 projects show that DAFL performs significantly better than baselines.

The center symmetric pattern (CSP) was widely used in the local binary pattern based facial feature, whereas never used to develop the illumination invariant measure in the literature. This paper proposes a novel diagonal symmetric pattern (DSP) to develop the illumination invariant measure for severe illumination variation face recognition. Firstly, the subtraction of two diagonal symmetric pixels is defined as the DSP unit in the face local region, which may be positive or negative. The DSP model is obtained by combining the positive and negative DSP units in the even × even block region. Then, the DSP model can be used to generate several DSP images based on the 2 × 2 block or the 4 × 4 block by controlling the proportions of positive and negative DSP units, which results in the DSP2 image or the DSP4 image. The single DSP2 or DSP4 image with the arctangent function can develop the DSP2-face or the DSP4-face. Multi DSP2 or DSP4 images employ the extended sparse representation classification (ESRC) as the classifier that can form the DSP2 images based classification (DSP2C) or the DSP4 images based classification (DSP4C). Further, the DSP model is integrated with the pre-trained deep learning (PDL) model to construct the DSPPDL model. Finally, the experimental results on the Extended Yale B, CMU PIE, AR, and VGGFace2 face databases indicate that the proposed methods are efficient to tackle severe illumination variations.

An underlying assumption in bearing fault diagnosis is that the training data from a source domain and the test data from a target domain obey the same distribution. But this assumption can be easily violated in practical industrial environments due to domain shift, which leads to significant performance degradation. To overcome this issue, we propose a novel convolutional neural network model to identify cross-domain bearing fault types based on 1-D vibration signals. Different from current single-network-based approaches, our model comprises a student network and a teacher network that simultaneously conduct data distribution matching and discriminative feature learning. Moreover, the two networks promote each other with the label prediction consistency constraint, so that the discriminative knowledge is able to transfer between the domains. Our model bridges the semantic information of the source vibration signals and the distribution information of the target vibration signals by jointly performing cross-domain feature disentanglement and adaptation. The proposed method is evaluated extensively on the Case Western Reserve University bearing fault dataset in two scenarios: varying working loads and different sensor locations. Experimental results show the superior performance of our method compared with existing shallow and deep learning methods in the literature.

Siamese region proposal network has made remarkable achievements in visual object tracking because of its balanced accuracy and speed. However, it regards tracking as a local one-shot detection task, which lose the power of updating the appearance model online thereby cannot handle the object-occlusion, fast motion and out-of-view situations. To tackle this problem, we propose a method that combines adaptive Kalman filter with Siamese region proposal network (Anti-occlusion-SiamRPN) to make full use of the object spatial-temporal information. Specifically we first extract target features through deep network and then uses adaptive Kalman filter to predict target trajectory in these difficult scenarios. Further this trajectory is used to select the candidate area of the next frame for Siamese region proposal network, which improve the searching mechanism. In this way, the introduction of adaptive Kalman filter makes the tracking process online learning which makes up for the disadvantage that Siamese region proposal network can only track offline. In addition, a hard example discrimination method (HEDM) is proposed to estimate whether the occlusion occurs and how seriously it is, which also improve Kalman filtering mechanism to make it update adaptively. Our method being evaluated with the speed of 80 FPS on five widely-applied challenging benchmarks including OTB2013, OTB2015, OTB50, VOT2016 and VOT2018. The extensive experimental results demonstrate our method achieves state-of-the-art effects and great improvement in comparison to other trackers.

NAND flash memory is widely used in various computing systems. However, flash blocks can sustain only a limited number of program/erase (P/E) cycles, which are referred to as the endurance. On one hand, in order to ensure data integrity, flash manufacturers often define the maximum P/E cycles of the worst block as the endurance of flash blocks. On the other hand, blocks exhibit large endurance variations, which introduce two serious problems. The first problem is that the error correcting code (ECC) is often over-provisioned, as it has to be designed to tolerate the worst case to ensure data integrity, which causes longer decoding latency. The second problem is the underutilized block's lifespan due to conservatively defined block endurance. Raw bit error rate (RBER) of most blocks have not arrived the allowable RBER based on the nominal endurance point, which implies that the conventional P/E cycle-based block retirement policies may waste large flash storage space. In this paper, to exploit the storage capacity of each flash block, we propose an RBER-aware lifetime prediction scheme based on machine learning technologies. We consider the problem that the model can lose prediction effectiveness over time and use incremental learning to update the model for adapting the changes at different lifetime stages. At run time, trained data will be gradually discarded, which can reduce memory overhead. For evaluating our purpose, four well-known machine learning techniques have been compared in terms of predictive accuracy and time overhead under our proposed lifetime prediction scheme. We also compared the predicted values with the tested values obtained in the real NAND flash-based test platform, and the experimental results show that the support vector machine (SVM) models based on our proposed lifetime prediction scheme can achieve as high as 95% accuracy for flash blocks. We also apply our proposed lifetime prediction scheme to predict the actual endurance of flash blocks at four different retention times, and the experimental results show that it can significantly improve the maximum P/E cycle of flash blocks from 37.5% to 86.3% on average. Therefore, the proposed lifetime prediction scheme can provide a guide for block endurance prediction.

Median filtering (MF), a non-linear smoothing operation, has often been utilized as a means of image denoising to protect image edges and hide the traces of image tampering. Although the existing MF forensics methods have achieved excellent performance without post-processing, there is still a challenge of detecting MF in small image size and JPEG compression scenario. To meet this challenge, a robust MF forensic method using convolutional-neural-network (CNN)-based multiple residuals learning is proposed in this paper. Firstly, to reveal the traces left by MF, we use multiple high-pass filters to initialize the weights of the pre-processing layer, and obtain discriminative residuals to characterize MF artifacts in various aspects. Then the output of the pre-processing layer is employed as the input of CNN, which is elaborately designed to extract rich hierarchical features for further classification. Furthermore, Batch Normalization (BN) is introduced as a regularization method to help accelerate convergence of the entire network. The extensive experimental results on the composite database demonstrate that the proposed method is superior to the state-of-the-art methods when detecting MF in both JPEG compressed and small size images.

3D-multi-level cell (MLC) NAND flash memory adopts 3D stack technology and stores two bits per cell, leading to improved storage capacities, but sacrificing data reliability. Low-density parity-check (LDPC) codes showing strong error correction capability benefit from their soft decision decoding, which is widely exploited to guarantee data reliability. Nevertheless, adopting LDPC codes can introduce a concern about read performance, because their iterative soft-decision decoding requires LogLikelihood Ratio (LLR) information, called soft decision information, by applying multi-sensing voltages. This process of obtaining LLR information leads to high sensing and transferring latencies, lowering down 3D-MLC read performance. In particular, when raw bit error rates (RBER) are much higher due to the long retention periods and program/erase (P/E) cycles, this problem becomes more serious. In this paper, we propose a RBER-aware multi-sensing scheme for reducing sensing and transferring latencies, and thus improving read performance. This proposed scheme exploits the variations of RBER in flash pages with the increase of retention time and P/E cycles to dynamically apply sensing voltages. Simulation results show that this scheme significantly decreases the number of required sensing voltages while maintaining LDPC error correction capability, enhancing 3D-MLC read performance.