Recently, owing to their excellent flexibility and adaptability, skin-like pressure and strain sensors integrated with the human body have the potential for great prospects in healthcare. This review mainly focuses on the representative advances of the flexible pressure and strain sensors for health monitoring in recent years. The review consists of five sections. Firstly, we give a brief introduction of flexible skin-like sensors and their primary demands, and we comprehensively outline the two categories of design strategies for flexible sensors. Secondly, combining the typical sensor structures and their applications in human body monitoring, we summarize the recent development of flexible pressure sensors based on perceptual mechanism, the sensing component, elastic substrate, sensitivity and detection range. Thirdly, the main structure principles and performance characteristic parameters of noteworthy flexible strain sensors are summed up, namely the sensing mechanism, sensitive element, substrate, gauge factor, stretchability, and representative applications for human monitoring. Furthermore, the representations of flexible sensors with the favorable biocompatibility and self-driven properties are introduced. Finally, in conclusion, besides continuously researching how to enhance the flexibility and sensitivity of flexible sensors, their biocompatibility, versatility and durability should also be given sufficient attention, especially for implantable bioelectronics. In addition, the discussion emphasizes the challenges and opportunities of the above highlighted characteristics of novel flexible skin-like sensors.

In order to improve the prediction accuracy, this paper proposes a short-term power load forecasting method based on the improved exponential smoothing grey model. It firstly determines the main factor affecting the power load using the grey correlation analysis. It then conducts power load forecasting using the improved multivariable grey model. The improved prediction model firstly carries out the smoothing processing of the original power load data using the first exponential smoothing method. Secondly, the grey prediction model with an optimized background value is established using the smoothed sequence which agrees with the exponential trend. Finally, the inverse exponential smoothing method is employed to restore the predicted value. The first exponential smoothing model uses the 0.618 method to search for the optimal smooth coefficient. The prediction model can take the effects of the influencing factors on the power load into consideration. The simulated results show that the proposed prediction algorithm has a satisfactory prediction effect and meets the requirements of short-term power load forecasting. This research not only further improves the accuracy and reliability of short-term power load forecasting but also extends the application scope of the grey prediction model and shortens the search interval.

Visual place recognition is a challenging problem in robotics and autonomous systems because the scene undergoes appearance and viewpoint changes in a changing world. Existing state-of-the-art methods heavily rely on CNN-based architectures. However, CNN cannot effectively model image spatial structure information due to the inherent locality. To address this issue, this paper proposes a novel Transformer-based place recognition method to combine local details, spatial context, and semantic information for image feature embedding. Firstly, to overcome the inherent locality of the convolutional neural network (CNN), a hybrid CNN-Transformer feature extraction network is introduced. The network utilizes the feature pyramid based on CNN to obtain the detailed visual understanding, while using the vision Transformer to model image contextual information and aggregate task-related features dynamically. Specifically, the multi-level output tokens from the Transformer are fed into a single Transformer encoder block to fuse multi-scale spatial information. Secondly, to acquire the multi-scale semantic information, a global semantic NetVLAD aggregation strategy is constructed. This strategy employs semantic enhanced NetVLAD, imposing prior knowledge on the terms of the Vector of Locally Aggregated Descriptors (VLAD), to aggregate multi-level token maps, and further concatenates the multi-level semantic features globally. Finally, to alleviate the disadvantage that the fixed margin of triplet loss leads to the suboptimal convergence, an adaptive triplet loss with dynamic margin is proposed. Extensive experiments on public datasets show that the learned features are robust to appearance and viewpoint changes and achieve promising performance compared to state-of-the-arts.

Loop closure detection is a key module for visual simultaneous localization and mapping (SLAM). Most previous methods for this module have not made full use of the information provided by images, i.e., they have only used the visual appearance or have only considered the spatial relationships of landmarks; the visual, spatial and semantic information have not been fully integrated. In this paper, a robust loop closure detection approach integrating visual–spatial–semantic information is proposed by employing topological graphs and convolutional neural network (CNN) features. Firstly, to reduce mismatches under different viewpoints, semantic topological graphs are introduced to encode the spatial relationships of landmarks, and random walk descriptors are employed to characterize the topological graphs for graph matching. Secondly, dynamic landmarks are eliminated by using semantic information, and distinctive landmarks are selected for loop closure detection, thus alleviating the impact of dynamic scenes. Finally, to ease the effect of appearance changes, the appearance-invariant descriptor of the landmark region is extracted by a pre-trained CNN without the specially designed manual features. The proposed approach weakens the influence of viewpoint changes and dynamic scenes, and extensive experiments conducted on open datasets and a mobile robot demonstrated that the proposed method has more satisfactory performance compared to state-of-the-art methods.