Differentiation between benign and malignant breast cancer cases in X-ray images can be difficult due to their similar features. In recent studies, the transfer learning technique has been used to classify benign and malignant breast cancer by fine-tuning various pre-trained networks such as AlexNet, visual geometry group (VGG), GoogLeNet, and residual network (ResNet) on breast cancer datasets. However, these pre-trained networks have been trained on large benchmark datasets such as ImageNet, which do not contain labeled images related to breast cancers which lead to poor performance. In this research, we introduce a novel technique based on the concept of transfer learning, called double-shot transfer learning (DSTL). DSTL is used to improve the overall accuracy and performance of the pre-trained networks for breast cancer classification. DSTL updates the learnable parameters (weights and biases) of any pre-trained network by fine-tuning them on a large dataset that is similar to the target dataset. Then, the updated networks are fine-tuned with the target dataset. Moreover, the number of X-ray images is enlarged by a combination of augmentation methods including different variations of rotation, brightness, flipping, and contrast to reduce overfitting and produce robust results. The proposed approach has demonstrated a significant improvement in classification accuracy and performance of the pre-trained networks, making them more suitable for medical imaging.

Inspired by Connected-UNets, this study proposes a deep learning model, called Connected-SegNets, for breast tumor segmentation from X-ray images. In the proposed model, two SegNet architectures are connected with skip connections between their layers. Moreover, the cross-entropy loss function of the original SegNet has been replaced by the intersection over union (IoU) loss function in order to make the proposed model more robust against noise during the training process. As part of data preprocessing, a histogram equalization technique, called contrast limit adapt histogram equalization (CLAHE), is applied to all datasets to enhance the compressed regions and smooth the distribution of the pixels. Additionally, two image augmentation methods, namely rotation and flipping, are used to increase the amount of training data and to prevent overfitting. The proposed model has been evaluated on two publicly available datasets, specifically INbreast and the curated breast imaging subset of digital database for screening mammography (CBIS-DDSM). The proposed model has also been evaluated using a private dataset obtained from Cheng Hsin General Hospital in Taiwan. The experimental results show that the proposed Connected-SegNets model outperforms the state-of-the-art methods in terms of Dice score and IoU score. The proposed Connected-SegNets produces a maximum Dice score of 96.34% on the INbreast dataset, 92.86% on the CBIS-DDSM dataset, and 92.25% on the private dataset. Furthermore, the experimental results show that the proposed model achieves the highest IoU score of 91.21%, 87.34%, and 83.71% on INbreast, CBIS-DDSM, and the private dataset, respectively.

Agriculture is an important regional economic industry in Asian regions. Ensuring food security and stabilizing the food supply are a priority. In response to the frequent occurrence of natural disasters caused by global warming in recent years, the Agriculture and Food Agency (AFA) in Taiwan has conducted agricultural and food surveys to address those issues. To improve the accuracy of agricultural and food surveys, AFA uses remote sensing technology to conduct surveys on the planting area of agricultural crops. Unlike optical images that are easily disturbed by rainfall and cloud cover, synthetic aperture radar (SAR) images will not be affected by climatic factors, which makes them more suitable for the forecast of crops production. This research proposes a novel spatial-temporal neural network called a convolutional long short-term memory rice field classifier (ConvLSTM-RFC) for rice field classification from Sentinel-1A SAR images of Yunlin and Chiayi counties in Taiwan. The proposed model ConvLSTM-RFC is implemented with multiple convolutional long short-term memory attentions blocks (ConvLSTM Att Block) and a bi-tempered logistic loss function (BiTLL). Moreover, a convolutional block attention module (CBAM) was added to the residual structure of the ConvLSTM Att Block to focus on rice detection in different periods on SAR images. The experimental results of the proposed model ConvLSTM-RFC have achieved the highest accuracy of 98.08% and the rice false positive is as low as 15.08%. The results indicate that the proposed ConvLSTM-RFC produces the highest area under curve (AUC) value of 88% compared with other related models.

The Internet of Things (IoT) technology has revolutionized the healthcare industry by enabling a new paradigm for healthcare delivery. This paradigm is known as the Internet of Medical Things (IoMT). IoMT devices are typically connected via a wide range of wireless communication technologies, such as Bluetooth, radio-frequency identification (RFID), ZigBee, Wi-Fi, and cellular networks. The ZigBee protocol is considered to be an ideal protocol for IoMT communication due to its low cost, low power usage, easy implementation, and appropriate level of security. However, maintaining ZigBee’s high reliability is a major challenge due to multi-path fading and interference from coexisting wireless networks. This has increased the demand for more efficient channel coding schemes that can achieve a more reliable transmission of vital patient data for ZigBee-based IoMT communications. To meet this demand, a novel coding scheme called inter-multilevel super-orthogonal space–time coding (IM-SOSTC) can be implemented by combining the multilevel coding and set partitioning of super-orthogonal space–time block codes based on the coding gain distance (CGD) criterion. The proposed IM-SOSTC utilizes a technique that provides inter-level dependency between adjacent multilevel coded blocks to facilitate high spectral efficiency, which has been compromised previously by the high coding gain due to the multilevel outer code. In this paper, the performance of IM-SOSTC is compared to other related schemes via a computer simulation that utilizes the quasi-static Rayleigh fading channel. The simulation results show that IM-SOSTC outperforms other related coding schemes and is capable of providing the optimal trade-off between coding gain and spectral efficiency whilst guaranteeing full diversity and low complexity.

This study proposed an improved full-scale aggregated MobileUNet (FA-MobileUNet) model to achieve more complete detection results of oil spill areas using synthetic aperture radar (SAR) images. The convolutional block attention module (CBAM) in the FA-MobileUNet was modified based on morphological concepts. By introducing the morphological attention module (MAM), the improved FA-MobileUNet model can reduce the fragments and holes in the detection results, providing complete oil spill areas which were more suitable for describing the location and scope of oil pollution incidents. In addition, to overcome the inherent category imbalance of the dataset, label smoothing was applied in model training to reduce the model’s overconfidence in majority class samples while improving the model’s generalization ability. The detection performance of the improved FA-MobileUNet model reached an mIoU (mean intersection over union) of 84.55%, which was 17.15% higher than that of the original U-Net model. The effectiveness of the proposed model was then verified using the oil pollution incidents that significantly impacted Taiwan’s marine environment. Experimental results showed that the extent of the detected oil spill was consistent with the oil pollution area recorded in the incident reports.

A new space-time coding scheme is drawn based upon the concepts of multilevel coding, space-time block coding (STBC), and spatial modulation (SM). In light of a STBC-SM scheme, an interblock-correlated multilevel code is combined in conjunction with set partitioning of the expanded transmission matrix set according to the coding gain distance criterion. The error performance of an example code is compared with the traditional STBC-SM scheme in computer simulation. Under the situation of the same spectral efficiency and space diversity order, the proposed scheme is superior as regards its bit error performance.