AIM in Alternative Medicine

Alternative medicine (AM) is one of the medical fields that use more natural and traditional therapies for disease diagnosis and treatment, in which traditional Chinese medicine (TCM) now has been recognized as one of the main approaches of AM. As a clinical and evidencedriven discipline with long histories, AM is also heavily relied on in the utilization of big healthcare and therapeutic data for improving the capability of diagnosis and treatment. In particular, artificial intelligence (AI) has been widely adopted in AM to deliver more practical and feasible intelligent solutions for clinical operations since 1970s. This chapter summarizes the main approaches, related typical applications, and future directions of AI in AM to give related researchers a brief useful reference. We find that although AM has not been widely used in clinical practice internationally, the AI studies showed abundant experiences and technique trials in expert system, machine learning, data mining, knowledge graph, and deep learning. In addition, various types of data, such as bibliographic literatures, electronic medical records, and images were used in the related AI tasks and studies. Furthermore, during this COVID-19 pandemic era, we have witnessed the clinical effectiveness of TCM for COVID-19 treatment, which mostly was detected by real-world data mining applications. This indicates the potential opportunity of the booming of AI research and applications in various aspects (e.g., effective clinical therapy discovery and network pharmacology of AM drugs) in AM fields. © Springer Nature Switzerland AG 2022.

Thermal and Electrical Performance of Negative Capacitance FinFET on GaAs

Along with the COVID-19 pandemic and the large-scale application of 5G, IoT has become more critical for our daily lives. GaAs is a promising semiconductor for field effect transistors in IoT applications. Due to the high electron mobility of GaAs, n-type FinFET based on GaAs is expected with a higher conductance and electron velocity than Silicon. FinFET based on GaAs has a lower subthreshold swing (SS) and higher Ion/Ioff than FinFET based on Silicon, particularly at high temperatures.Negative Capacitance FinFET(NC-FinFET) is an important emerging technology for low-power applications. To further enhance the performance of the GaAs FinFET, we incorporate Hf0.5Zr0.5O2 films in the gate to achieve Negative Capacitance (NC). The NC effect brings a higher Ion/Ioff and a negative coefficient to reduce the SS of the FinFET. Our simulation research proves the GaAs-NC-FinFET has the slightest SS variation in 300K-400K and maximum Ion/Ioff compared with other FinFETs. © 2022 IEEE.

Image Segmentation For pneumothorax disease Based On based on Nested Unet Model

Pneumothorax on lung can be caused by a blunt chest injury, damage from underlying lung disease or Covid-19 Virus. Using CT scanning to examine high-risk people is an important task for many doctors and hospital. With the development of machine learning techniques, computer-aided diagnosis is widely used in pneumothorax detection. In this paper, we proposed a nested Unet model with a backbone of EfficientNet. This model used many skip pathway connections in many layers to reduce the semantic gap between networks. We choose dice loss as our experiment metrics, which is widely used in segmentation task. The lower Dice loss is, the better performance the model has. Compared with the simple Unet model or the other models, the experiments show that our model has better performance. © 2022 IEEE.

AbGradCon 2021: lessons in digital meetings, international collaboration, and interdisciplinarity in astrobiology

The Astrobiology Graduate Conference (AbGradCon) is an annual conference both organized for and by early-career researchers, postdoctoral fellows, and students as a way to train the next generation of astrobiologists and develop a robust network of cohorts moving forward. AbGradCon 2021 was held virtually on 14-17 September 2021, hosted by the Earth-Life Science Institute (ELSI) of Tokyo Institute of Technology after postponement of the in-person event in 2020 due to the COVID-19 pandemic. The meeting consisted of presentations by 120 participants from a variety of fields, two keynote speakers, and other career-building events and workshops. Here, we report on the organizational and executional aspects of AbGradCon 2021, including the meeting participant demographics, various digital aspects introduced specifically for a virtual edition of the meeting, and the submission and evaluation process. The evaluation process of AbGradCon 2021 is unique in that all evaluations are done by the peers of the applicants, and as astrobiology is inherently a broad discipline, the evaluation process revealed a number of trends related to multidisciplinarity of the astrobiology field. We believe that meetings like AbGradCon can provide a unique opportunity for students and early career researchers in astrobiology to experience community building, inter- and multidisciplinary collaboration, and career training and would be a welcome sight in other fields as well. We hope that this report provides inspiration and a basic roadmap for organizing future conferences in any field with similar goals.

Link Prediction based on Tensor Decomposition for the Knowledge Graph of COVID-19 Antiviral Drug

Due to the large-scale spread of COVID-19, which has a significant impact on human health and social economy, developing effective antiviral drugs for COVID-19 is vital to saving human lives. Various biomedical associations, e.g., drug-virus and viral protein-host protein interactions, can be used for building biomedical knowledge graphs. Based on these sources, large-scale knowledge reasoning algorithms can be used to predict new links between antiviral drugs and viruses. To utilize the various heterogeneous biomedical associations, we proposed a fusion strategy to integrate the results of two tensor decomposition-based models (i.e., CP-N3 and ComplEx-N3). Sufficient experiments indicated that our method obtained high performance (MRR=0.2328). Compared with CP-N3, the mean reciprocal rank (MRR) is increased by 3.3% and compared with ComplEx-N3, the MRR is increased by 3.5%. Meanwhile, we explored the relationship between the performance and relationship types, which indicated that there is a negative correlation (PCC=0.446, P-value=2.26e-194) between the performance of triples predicted by our method and edge betweenness.