Emotion is the human brain reacting to objective things. In real life, human emotions are complex and changeable, so research into emotion recognition is of great significance in real life applications. Recently, many deep learning and machine learning methods have been widely applied in emotion recognition based on EEG signals. However, the traditional machine learning method has a major disadvantage in that the feature extraction process is usually cumbersome, which relies heavily on human experts. Then, end-to-end deep learning methods emerged as an effective method to address this disadvantage with the help of raw signal features and time-frequency spectrums. Here, we investigated the application of several deep learning models to the research field of EEG-based emotion recognition, including deep neural networks (DNN), convolutional neural networks (CNN), long short-term memory (LSTM), and a hybrid model of CNN and LSTM (CNN-LSTM). The experiments were carried on the well-known DEAP dataset. Experimental results show that the CNN and CNN-LSTM models had high classification performance in EEG-based emotion recognition, and their accurate extraction rate of RAW data reached 90.12 and 94.17%, respectively. The performance of the DNN model was not as accurate as other models, but the training speed was fast. The LSTM model was not as stable as the CNN and CNN-LSTM models. Moreover, with the same number of parameters, the training speed of the LSTM was much slower and it was difficult to achieve convergence. Additional parameter comparison experiments with other models, including epoch, learning rate, and dropout probability, were also conducted in the paper. Comparison results prove that the DNN model converged to optimal with fewer epochs and a higher learning rate. In contrast, the CNN model needed more epochs to learn. As for dropout probability, reducing the parameters by ~50% each time was appropriate.

Identification efficiency is a key performance metrics to evaluate the ultra high frequency (UHF) based radio frequency identification (RFID) systems. In order to solve the tag collision problem and improve the identification rate in large scale networks, we propose a collision arbitration strategy termed as group-based binary splitting algorithm (GBSA), which is an integration of an efficient tag cardinality estimation method, an optimal grouping strategy and a modified binary splitting. In GBSA, tags are properly divided into multiple subsets according to the tag cardinality estimation and the optimal grouping strategy. In case that multiple tags fall into a same time slot and form a subset, the modified binary splitting strategy will be applied while the rest tags are waiting in the queue and will be identified in the following slots. To evaluate its performance, we first derive the closed-form expression of system throughput for GBSA. Through the theoretical analysis, the optimal grouping factor is further determined. Extensive simulation results supplemented by prototyping tests indicate that the system throughput of our proposed algorithm can reach as much as 0.4835, outperforming the existing anti-collision algorithms for UHF RFID systems.

The remote sensing scene images classification has been of great value to civil and military fields. Deep learning models, especially the convolutional neural network (CNN), have achieved great success in this task, however, they may suffer from two challenges: first, the sizes of the category objects are usually different, but the conventional CNN extracts the features with fixed convolution extractor, which could cause the failure in learning the multiscale features; second, some image regions may not be useful during the feature learning process, therefore, how to guide the network to select and focus on the most relevant regions is crucially vital for remote sensing scene image classification. To address these two challenges, we propose a multiscale attention network (MSA-Network), which integrates a multiscale (MS) module and a channel and position attention (CPA) module to boost the performance of the remote sensing scene classification. The proposed MS module learns multiscale features by adopting various sizes of sliding windows from different depths’ layers and receptive fields. The CPA module is composed of two parts: the channel attention (CA) module and the position attention (PA) one. The CA module learns the global attention features from channel-level, and the PA module extracts the local attention features from pixel-level. Thus, fusing both of those two attention features, the network is apt to focus on the more critical and salient regions automatically. Extensive experiments on UC Merced, AID, NWPU-RESISC45 datasets demonstrate that the proposed MSA-Network outperforms several state-of-the-art methods.

Attributable to the emergence of mobile edge computing (MEC), the hardware-constrained industrial devices have further computational and service capability in industrial Internet of Things (IIoT) systems. Nevertheless, unreliable network environments and unpredictable processing delays are intolerable factors for any service application. Therefore, this article studies the associated constraint problem of how to optimize the offloading decision and resource allocation in collaborative edge computing networks with multiple IIoT devices and MEC servers. In order to attain this purpose, the optimization problem is mathematically derived as a mixed-integer nonlinear programming problem which is a large-scale NP-hard problem. Then, an improved differential evolution algorithm (IDE) is proposed to obtain the optimal solutions in an accessible time complexity. Finally, the performance of the IDE-based resource allocation scheme has been compared with other baseline schemes. Simulation results demonstrate that the IDE-based optimization scheme could significantly reduce the system delay and energy consumption.