A wireless sensor network (WSN) is an essential component of the Internet of Things (IoTs) for information exchange and communication between ubiquitous smart objects. Clustering techniques are widely applied to improve network performance during the routing phase for WSN. However, existing clustering methods still have some drawbacks such as uneven distribution of cluster heads (CH) and unbalanced energy consumption. Recently, much attention has been paid to intelligent clustering methods based on machine learning to solve the above issues. In this paper, an affinity propagation-based self-adaptive (APSA) clustering method is presented. The advantage of K-medoids, which is a traditional machine learning algorithm, is combined with the affinity propagation (AP) method to achieve more reasonable clustering performance. AP is firstly utilized to determine the number of CHs and to search for the optimal initial cluster centers for K-medoids. Then the modified K-medoids is utilized to form the topology of the network by iteration. The presented method effectively avoids the weakness of the traditional K-medoids in aspects of the homogeneous clustering and convergence rate. Simulation results show that the proposed algorithm outperforms some latest work such as the unequal cluster-based routing scheme for multi-level heterogeneous WSN (UCR-H), the low-energy adaptive clustering hierarchy using affinity propagation (LEACH-AP) algorithm, and the energy degree distance unequal clustering (EDDUCA) algorithm.

Many remote sensing scene classification algorithms improve their classification accuracy by additional modules, which increases the parameters and computing overhead of the model at the inference stage. In this paper, we explore how to improve the classification accuracy of the model without adding modules at the inference stage. First, we propose a network training strategy of training with multi-size images. Then, we introduce more supervision information by triplet loss and design a branch for the triplet loss. In addition, dropout is introduced between the feature extractor and the classifier to avoid over-fitting. These modules only work at the training stage and will not bring about the increase in model parameters at the inference stage. We use Resnet18 as the baseline and add the three modules to the baseline. We perform experiments on three datasets: AID, NWPU-RESISC45, and OPTIMAL. Experimental results show that our model combined with the three modules is more competitive than many existing classification algorithms. In addition, ablation experiments on OPTIMAL show that dropout, triplet loss, and training with multi-size images improve the overall accuracy of the model on the test set by 0.53%, 0.38%, and 0.7%, respectively. The combination of the three modules improves the overall accuracy of the model by 1.61%. It can be seen that the three modules can improve the classification accuracy of the model without increasing model parameters at the inference stage, and training with multi-size images brings a greater gain in accuracy than the other two modules, but the combination of the three modules will be better.

Wireless Sensor Networks (WSNs) are usually troubled with constrained energy and complicated network topology which can be mitigated by introducing a mobile agent node. Due to the numerous nodes present especially in large scale networks, it is time-consuming for the collector to traverse all nodes, and significant latency exists within the network. Therefore, the moving path of the collector should be well scheduled to achieve a shorter length for efficient data gathering. Much attention has been paid to mobile agent moving trajectory panning, but the result has limitations in terms of energy consumption and network latency. In this paper, we adopt a hybrid method called HM-ACOPSO which combines ant colony optimization (ACO) and particle swarm optimization (PSO) to schedule an efficient moving path for the mobile agent. In HM-ACOPSO, the sensor field is divided into clusters, and the mobile agent traverses the cluster heads (CHs) in a sequence ordered by ACO. The anchor node of each CHs is selected in the range of communication by the mobile agent using PSO based on the traverse sequence. The communication range adjusts dynamically, and the anchor nodes merge in a duplicated covering area for further performance improvement. Numerous simulation results prove that the presented method outperforms some similar works in terms of energy consumption and data gathering efficiency.

RFID (Radio frequency identification) and wireless sensor networks are backbone technologies for pervasive environments. In integration of RFID and WSN, RFID data uses WSN protocols for multi-hop communications. Energy is a critical issue in WSNs; however, RFID data contains a lot of duplication. These duplications can be eliminated at the base station, but unnecessary transmissions of duplicate data within the network still occurs, which consumes nodes’ energy and affects network lifetime. In this paper, we propose an in-network RFID data filtering scheme that efficiently eliminates the duplicate data. For this we use a clustering mechanism where cluster heads eliminate duplicate data and forward filtered data towards the base station. Simulation results prove that our approach saves considerable amounts of energy in terms of communication and computational cost, compared to existing filtering schemes.

In today’s society, time is considered more valuable than money, and researchers often have limited time to find relevant papers for their research. Identifying and accessing essential information can be a challenge in this situation. To address this, the personalized suggestion system has been developed, which uses a user’s behavior data to suggest relevant items. The collaborative filtering strategy has been used to provide a user with the top research articles based on their queries and similarities with other users’ questions, thus saving time by avoiding time-consuming searches. However, when rating data is abundant but sparse, the usual method of determining user similarity is relatively straightforward. Furthermore, it fails to account for changes in users’ interests over time resulting in poor performance. This research proposes a new similarity measure approach that takes both user confidence and time context into account to increase user similarity computation. The experimental results show that the proposed technique works well with sparse data, and improves accuracy by 16.2% compared to existing models, especially during prediction. Furthermore, it enhances the quality of recommendations.