SPSC: Stream Processing Framework Atop Serverless Computing for Industrial Big Data.

With the advance of smart manufacturing and information technologies, the volume of data to process is increasing accordingly. Current solutions for big data processing resort to distributed stream processing systems, such as Apache Flink and Spark. However, such frameworks face challenges of resource underutilization and high latency in big data application scenarios. In this article, we propose SPSC, a serverless-based stream computing framework where events are discretized into the atomic stream and stateless Lambda functions are taken as context-irrelevant operators, achieving task parallelism and inherent data parallelism in processing. Also, we implement a prototype of the framework on Amazon Web service (AWS) using AWS Lambda, AWS simple queue service, and AWS DynamoDB. The evaluation shows that compared with Alibaba's real-time computing Flink version, SPSC outperforms by 10.12% when the overhead is close.

π-π stack driven competitive /complementary adsorption of aromatic compounds on MIL-53(Al).

In this study, the selective adsorption of aromatic compounds on mesoporous MIL-53(Al) was investigated, and followed the order: Biphenyl (Biph) > Triclosan (TCS) > Bisphenol A (BPA) > Pyrogallol (Pyro) > Catechol (Cate) > Phenol (Phen), and exhibited high selectivity toward TCS in binary compounds. In addition to hydrophobicity and hydrogen bonding, π-π interaction/stacking predominated, and more evidently with double benzene rings. TCS-containing halogens could increase π interaction on the benzene rings via forming Cl-π stacking with MIL-53(Al). Moreover, site energy distribution confirmed that complementary adsorption mainly occurred in the Phen/TCS system, as evidenced by ΔQpri (the decreased solid-phase TCS concentration of the primary adsorbate) < Qsec (the solid-phase concentrations of the competitor (Phen)). In contrast, competitive sorption occurred in the BPA/TCS and Biph/TCS systems within 30 min due to ΔQpri = Qsec, followed by substitution adsorption in the BPA/TCS system, but not for the Biph/TCS system, likely attributed to the magnitude of energy gaps (Eg) and bond energy of TCS (1.80 eV, 362 kJ/mol) fallen between BPA (1.74 eV, 332 kJ/mol) and Biph (1.99 eV, 518 kJ/mol) according to the density-functional theory of Gaussian models. Biph with a more stable electronic homeostasis than TCS lead to the occurrence of substitution adsorption in the TCS/BPA system, but not in the TCS/Biph system. This study provides insight into the mechanisms of different aromatic compounds on MIL-53(Al).

MCAS-GP: Deep Learning-Empowered Middle Cerebral Artery Segmentation and Gate Proposition.

With the fast development of AI technologies, deep learning is widely applied for biomedical data analytics and digital healthcare. However, there remain gaps between AI-aided diagnosis and real-world healthcare demands. For example, hemodynamic parameters of the middle cerebral artery (MCA) have significant clinical value for diagnosing adverse perinatal results. Nevertheless, the current measurement procedure is tedious for sonographers. To reduce the workload of sonographers, we propose MCAS-GP, a deep learning-empowered framework that tackles the Middle Cerebral Artery Segmentation and Gate Proposition. MCAS-GP can automatically segment the region of the MCA and detect the corresponding position of the gate in the procedure of fetal MCA Doppler assessment. In MCAS-GP, a novel learnable atrous spatial pyramid pooling (LASPP) module is designed to adaptively learn multi-scale features. We also propose a novel evaluation metric, Affiliation Index, for measuring the effectiveness of the position of the output gate. To evaluate our proposed MCAS-GP, we build a large-scale MCA dataset, collaborating with the International Peace Maternity and Child Health Hospital of China welfare institute (IPMCH). Extensive experiments on the MCA dataset and two other public surgical datasets demonstrate that MCAS-GP can achieve considerable performance improvement in both accuracy and inference time.

Perceptual Data Augmentation for Biomedical Coronary Vessel Segmentation.

Sufficient annotated data is critical to the success of deep learning methods. Annotating for vessel segmentation in X-ray coronary angiograms is extremely difficult because of the small and complex structures to be processed. Although unsupervised domain adaptation methods can be utilized to alleviate the annotation burden by using data in other domains, e.g., eye fundus images, these methods cannot perform well due to the characteristic of medical images. Data augmentation can help improve the similarity of source domain and target domain in unsupervised domain adaptation tasks. Existing data augmentation methods play a limited role in improving domain adaptation performance, especially for special medical image segmentation tasks. In this paper, we propose an effective perceptual data augmentation method to improve the similarity between eye fundus images and coronary angiograms by synthesizing virtual samples. Auto Foreground Augment method is designed to search for geometric transformations that improve the similarity between foreground vessels of eye fundus images and coronary angiograms. The Haar Wavelet-Based Perceptual Similarity Index is utilized to guide the synthesis of virtual samples in foreground and background mixup. Extensive experiments show that our data augmentation method can synthesize high-quality virtual samples and thus improve the domain adaptation performance. To our best knowledge, this is the first work to apply perceptual data augmentation to vessel segmentation in coronary angiograms.