We theoretically investigate the plasmonic properties of mid-infrared graphene-based metamaterials and apply deep learning of a neural network for the inverse design. These artificial structures have square periodic arrays of graphene plasmonic resonators deposited on dielectric thin films. Optical spectra vary significantly with changes in structural parameters. To validate our theoretical approach, we carry out finite difference time domain simulations and compare computational results with theoretical calculations. Quantitatively good agreements among theoretical predictions, simulations, and previous experiments allow us to employ this proposed theoretical model to generate reliable data for training and testing deep neural networks. By merging the pre-trained neural network with the inverse network, we implement calculations for inverse design of the graphene-based metameterials. We also discuss the limitation of the data-driven approach.

The adoption of deep learning in ECG diagnosis is often hindered by the scarcity of large, well-labeled datasets in real-world scenarios, leading to the use of transfer learning to leverage features learned from larger datasets. Yet the prevailing assumption that transfer learning consistently outperforms training from scratch has never been systematically validated. In this study, we conduct the first extensive empirical study on the effectiveness of transfer learning in multi-label ECG classification, by investigating comparing the fine-tuning performance with that of training from scratch, covering a variety of ECG datasets and deep neural networks. Firstly, We confirm that fine-tuning is the preferable choice for small downstream datasets; however, it does not necessarily improve performance. Secondly, the improvement from fine-tuning declines when the downstream dataset grows. With a sufficiently large dataset, training from scratch can achieve comparable performance, albeit requiring a longer training time to catch up. Thirdly, fine-tuning can accelerate convergence, resulting in faster training process and lower computing cost. Finally, we find that transfer learning exhibits better compatibility with convolutional neural networks than with recurrent neural networks, which are the two most prevalent architectures for time-series ECG applications. Our results underscore the importance of transfer learning in ECG diagnosis, yet depending on the amount of available data, researchers may opt not to use it, considering the non-negligible cost associated with pre-training.

Wireless sensor networks (WSNs) are being utilized widely in many different industries, including agriculture, medicine, and the military. They contain many distributed sensors to monitor physical or environmental factors, such as temperature, humidity, pressure, etc. and use various communication technologies, including WiFi, radio frequency (RF), Bluetooth, and ZigBee. ZigBee is always a preferred choice for applications in WSNs. ZigBee has remarkable capabilities, such as saving energy and transmitting data over long distances. ZigBee end devices, as well as a ZigBee coordinator (ZC) and a ZigBee router (ZR), are crucial components of the WSNs. This article discusses the fundamentals of the ZigBee network, one of the most popular data transmission technologies in wireless sensor networks (WSNs). Additionally, we want to discuss the ZigBee communication technologies and their applications, particularly in the networks. Different scenarios for mobile agents including their routing protocols in WSNs are considered. Simulation results of different scenarios demonstrate how easily scalability can be achieved and provide a foundation for further ZigBee application development. At last, some conclusions and ideas are presented for considerations.

In binary classification problems, two classes of data seem to be different from each other. It is expected to be more complicated due to the clusters in each class also tend to be different. Traditional algorithms as Support Vector Machine (SVM), Twin Support Vector Machine (TSVM), or Least Square Twin Support Vector Machine (LSTSVM) cannot sufficiently exploit structural information with cluster granularity of the data, cause limitation in the ability to detect data trends. Structural Twin Support Vector Machine (S-TSVM) sufficiently exploits structural information with cluster granularity for learning a represented hyperplane. Therefore, the ability to describe the data of S-TSVM is better than that of TSVM and LSTSVM. However, for the datasets where each class consists of clusters of different trends, the S-TSVM’s ability to describe data seems restricted. Besides, the training time of S-TSVM has not been improved compared to TSVM. This paper proposes a new Weighted Least Square - Support Vector Machine (called WLS-SVM) for binary classification problems with a clusters-vs-class strategy. Experimental results show that WLS-SVM could describe the tendency of the distribution of cluster information. Furthermore, the WLS-SVM training time is faster than that of S-TSVM and TSVM, and the WLS-SVM accuracy is better than LSTSVM and TSVM in most cases.

The dominance of traditional paper-based ECG records in clinical settings poses a barrier to integrating AI for cardiovascular disease detection. The shift towards digital ECG is imperative yet hindered by the lack of reliable digitization tools. Our methodology comprises three key phases: lead segmentation, signal extraction, and scale conversion. Initially, we employ a pre-trained YOLOv8 single-shot detector to capture snapshots of 12 ECG leads. Then, each snapshot undergoes Otsu's technique for RGB to binary conversion, Hough transform for grid detection, and Viterbi's algorithm for sampling and extracting signal values in pixels. Finally, we convert these pixel values to voltage values by estimating grid resolution within the snapshot. To address uneven lengths in the extracted lead signals, we use cubic spline interpolation to horizontally scale the signals to align with a predetermined target length while preserving their waveform.