To protect the environment and achieve the Sustainable Development Goals (SDGs), reducing greenhouse gas emissions has been actively promoted by global governments. Thus, clean energy, such as wind power, has become a very important topic among global governments. However, accurately forecasting wind power output is not a straightforward task. The present study attempts to develop a fuzzy seasonal long short-term memory network (FSLSTM) that includes the fuzzy decomposition method and long short-term memory network (LSTM) to forecast a monthly wind power output dataset. LSTM technology has been successfully applied to forecasting problems, especially time series problems. This study first adopts the fuzzy seasonal index into the fuzzy LSTM model, which effectively extends the traditional LSTM technology. The FSLSTM, LSTM, autoregressive integrated moving average (ARIMA), generalized regression neural network (GRNN), back propagation neural network (BPNN), least square support vector regression (LSSVR), and seasonal autoregressive integrated moving average (SARIMA) models are then used to forecast monthly wind power output datasets in Taiwan. The empirical results indicate that FSLSTM can obtain better performance in terms of forecasting accuracy than the other methods. Therefore, FSLSTM can efficiently provide credible prediction values for Taiwan’s wind power output datasets.

The segmentation of brain tumors in medical images is a crucial step of clinical treatment. Manual segmentation is time consuming and labor intensive, and existing automatic segmentation methods suffer from issues such as numerous parameters and low precision. To resolve these issues, this study proposes a learnable group convolution-based segmentation method that replaces convolution in the feature extraction stage with learnable group convolution, thereby reducing the number of convolutional network parameters and enhancing communication between convolution groups. To improve utilization of the feature maps, we added a skip connection structure between learnable group convolution modules, which increased segmentation precision. We used deep supervision to combine output images in the network output stage to reduce overfitting and enhance the recognition capabilities of the network. We tested the proposed algorithm model using the open BraTS 2018 dataset. The experiment results revealed that the proposed model is superior to 3D U-Net and DMFNet and has better segmentation results for tumor cores than No New-Net and NVDLMED, the winning methods in the BraTS 2018 challenge. The segmentation precision of the proposed method with regard to whole tumors, enhancing tumors, and tumor cores was 90.25%, 80.36%, and 86.20%. Furthermore, the proposed method uses fewer parameters and a less complex model.

The purpose of this research was to understand the current physical and mental health of the elderly using sports apps under the COVID-19 pandemic. A total of 711 questionnaires were collected using purposive sampling and the snowball method and were analyzed by Statistical Product and Service Solutions 22.0 and Analysis of Moment Structures 20.0 software. The survey found that elderly people who exercise at intervals of one month are more physically and mentally stressed, but that different exercise frequencies also have different levels of physical and mental health problems; the lower the exercise intensity, the more obvious the negative emotions, the stronger or the less time they spend in exercise, and the greater the pressure of sports. In a high-risk social environment, even if the elderly use sports apps to exercise, they will still change the intensity and time of the exercise, but they will not change the frequency of exercise that has become a daily habit.

As the Artificial Intelligence Internet of Things (AIoT)-based unmanned convenience stores stand out in an increasingly challenging market, the consumer experience is more important than ever (CustomerThink, 2018). By employing new technologies, 7-Eleven, a leading chain convenience store in Taiwan, launched X-Store in 2018. While AIoT-based unmanned technology can help solve the problem of manpower shortages in the future, a question arises: will people accept this new technology for shopping? In view of this and based on the technology acceptance model (TAM), this study adds perceived risk as another variable to explore the impact of perceived usefulness, perceived ease of use, and attitudes toward using unmanned technology etc. factors on the purchase intentions of consumers in unattended convenience stores. The study further employs SPSS software for reliability and validity analyses, descriptive statistics, multivariate analysis of variance (MANOVA), and structural equation modeling (SEM) in order to explore the causal relationship among the variables herein. The main empirical findings show that consumers’ perceived ease of use and perceived usefulness positively affect consumers’ attitudes toward making purchases in X-Store, and via the moderating effect, perceived usefulness and attitudes toward X-Store consumption impact consumers’ behavioral intention of purchasing products in X-Store. In addition, perceived risk has a significant moderating effect on attitudes toward using X-Store and behavioral intentions. The empirical results also reveal that male consumers have significantly greater perceived usefulness, perceived ease of use, attitudes toward using, and behavioral intentions in comparison with female consumers. Finally, this study presents conclusions and recommendations based on the research results as reference for unattended convenience store operators and follow-up researchers.

General convolutional neural networks are unable to automatically adjust their receptive fields for the detection of pneumonia lesion regions. This study, therefore, proposes a pneumonia detection algorithm with automatic receptive field adjustment. This algorithm is a modified form of RetinaNet with selective kernel convolution incorporated into the feature extraction network ResNet. The resulting SK-ResNet automatically adjusts the size of the receptive field. The convolutional neural network can then generate prediction bounds with sizes corresponding to those of the targets. In addition, the authors aggregated the detection results with SK-ResNet50 and SK-ResNet152 for the feature extraction network to further enhancing average precision (AP). With a data set provided by the Radiological Society of North America, the proposed algorithm with SK-ResNet50 as the feature extraction network resulted in AP 50 that was 1.5% higher than that returned by RetinaNet. The number of images processed per second differed by only 0.45, which indicated that AP was increased while detection speed was maintained. After the detection results with the SK-ResNet50 and SK-ResNet152 as the feature extraction network were combined, AP 50 increased by 3.3% compared to the RetinaNet algorithm. The experimental results show that the proposed algorithm is effective at automatically adjusting the size of the receptive field based on the size of the target, as well as increasing AP with minimal reduction in speed.