Wireless Sensor Networks (WSNs) are a type of self-organizing networks with limited energy supply and communication ability. One of the most crucial issues in WSNs is to use an energy-efficient routing protocol to prolong the network lifetime. We therefore propose the novel Energy-Efficient Load Balancing Ant-based Routing Algorithm (EBAR) for WSNs. EBAR adopts a pseudo-random route discovery algorithm and an improved pheromone trail update scheme to balance the energy consumption of the sensor nodes. It uses an efficient heuristic update algorithm based on a greedy expected energy cost metric to optimize the route establishment. Finally, in order to reduce the energy consumption caused by the control overhead, EBAR utilizes an energy-based opportunistic broadcast scheme. We simulate WSNs in different application scenarios to evaluate EBAR with respect to performance metrics such as energy consumption, energy efficiency, and predicted network lifetime. The results of this comprehensive study show that EBAR provides a significant improvement in comparison to the state-of-the-art approaches EEABR, SensorAnt, and IACO.

Sentiment analysis of online Chinese buzzwords (OCBs) is important for healthy development of platforms, such as games and social networking, which can avoid transmission of negative emotions through prediction of users’ sentiment tendencies. Buzzwords have the characteristics of varying text length, irregular wording, ignoring syntactic and grammatical requirements, no complete semantic structure, and no obvious sentiment features. This results in interference and challenges to the sentiment analysis of such texts. Sentiment analysis also requires capturing effective sentiment features from deeper contextual information. To solve the above problems, we propose a deep learning model combining BERT and BiLSTM. The goal is to generate dynamic representations of OCB vectors in downstream tasks by fine-tuning the BERT model and to capture the rich information of the text at the embedding layer to solve the problem of static representations of word vectors. The generated word vectors are then transferred to the BiLSTM model for feature extraction to obtain the local and global semantic features of the text while highlighting the text sentiment polarity for sentiment classification. The experimental results show that the model works well in terms of the comprehensive evaluation index F1. Our model also has important significance and research value for sentiment analysis of irregular texts, such as OCBs.

Wireless Sensor Networks (WSNs) are a particular type of distributed self-managed network with limited energy supply and communication ability. The most significant challenge of a routing protocol is the energy consumption and the extension of the network lifetime. Many energy-efficient routing algorithms were inspired by the development of Ant Colony Optimisation (ACO). However, due to the inborn defects, ACO-based routing algorithms have a slow convergence behaviour and are prone to premature, stagnation phenomenon, which hinders further route discovery, especially in a large-scale network. This paper proposes a hybrid routing algorithm by combining the Artificial Fish Swarm Algorithm (AFSA) and ACO to address these issues. We utilise AFSA to perform the initial route discovery in order to find feasible routes quickly. In the route discovery algorithm, we present a hybrid algorithm by combining the crowd factor in AFSA and the pseudo-random route select strategy in ACO. Furthermore, this paper presents an improved pheromone update method by considering energy levels and path length. Simulation results demonstrate that the proposed algorithm avoids the routing algorithm falling into local optimisation and stagnation, whilst speeding up the routing convergence, which is more prominent in a large-scale network. Furthermore, simulation evaluation reports that the proposed algorithm exhibits a significant improvement in terms of network lifetime.

Image retrieval is becoming more and more important due to the rapid increase of the number of images on the web. To improve the efficiency of computing the similarity of images, hashing has moved into the focus of research. This paper proposes a Deep Attention-based Hash (DAH) retrieval model, which combines an attention module and a convolutional neural network to obtain hash codes with strong representability. Our DAH has the following features: The Hamming distance between the hash codes generated by similar images is small and the Hamming distance of hash codes of dissimilar images has a larger constant value. The quantitative loss from Euclidean distance to Hamming distance is minimized. DAH has a high image retrieval precision: We thoroughly compare it with ten state-of-the-art approaches on the CIFAR-10 dataset. The results show that the Mean Average Precision (MAP) of DAH reaches more than 92% in terms of 12, 24, 36 and 48 bit hash codes on CIFAR-10, which is better than what the state-of-art methods used for comparison can deliver.

With the frequent occurrence of private data breaches, it is now more necessary than ever to address how to protect private data. The combination of Ciphertext-Policy Attribute-Based Encryption (CP-ABE) and blockchain typically enables secure storage and sharing of data. However, in high-dimensional attribute domains, that is, the number of attributes is large, these schemes have issues such as low security of data protection, high computational overhead, and high cost of attribute revocation. This paper proposes a personal privacy data protection scheme for encryption and revocation of high-dimensional attribute domains to address these issues. The proposed scheme is made up of three components. Firstly, Fast High-dimensional Attribute Domain-based Message Encryption (HAD-FME) is proposed to improve data security and reduce computational cost. Secondly, an Attribute Revocation Mechanism Based on Sentry Mode (SM-ARM) is designed in combination with smart contracts. Lastly, a Blockchain-based Model for Personal Privacy Data Protection (BC-PPDP) is proposed by integrating HAD-FME with SM-ARM. The security analysis results show that HAD-FME proposed in this paper is secure under the DLIN assumption, and the attribute revocation satisfies both forward and backward security. Experiments show that HAD-FME has higher computational efficiency than existing schemes in the high-dimensional attribute domains, SM-ARM has lower revocation cost than existing attribute revocation mechanisms, and smart contracts and blockchain work well.

Adding an attention module to the deep convolution semantic segmentation network has significantly enhanced the network performance. However, the existing channel attention module focusing on the channel dimension neglects the spatial relationship, causing location noise to transmit to the decoder. In addition, the spatial attention module exemplified by self-attention has a high training cost and challenges in execution efficiency, making it unsuitable to handle large-scale remote sensing data. We propose an efficient vector pooling attention (VPA) module for building the channel and spatial location relationship. The module can locate spatial information better by performing a unique vector average pooling in the vertical and horizontal dimensions of the feature maps. Furthermore, it can also learn the weights directly by using the adaptive local cross-channel interaction. Multiple weight learning ablation studies and comparison experiments with the classical attention modules were conducted by connecting the VPA module to a modified DeepLabV3 network using ResNet50 as the encoder. The results show that the mIoU of our network with the addition of an adaptive local cross-channel interaction VPA module increases by 3% compared to the standard network on the MO-CSSSD. The VPA-based semantic segmentation network can significantly improve precision efficiency compared with other conventional attention networks. Furthermore, the results on the WHU Building dataset present an improvement in IoU and F1-score by 1.69% and 0.97%, respectively. Our network raises the mIoU by 1.24% on the ISPRS Vaihingen dataset. The VPA module can also significantly improve the network’s performance on small target segmentation.