VERD: Emergence of Product-Based Video E-Commerce Retrieval Dataset from User's Perspective.

Customer demands for product search are growing as a result of the recent growth of the e-commerce market. According to this trend, studies on object-centric retrieval using product images have emerged, but it is difficult to respond to complex user-environment scenarios and a search requires a vast amount of data. In this paper, we propose the Video E-commerce Retrieval Dataset (VERD), which utilizes user-perspective videos. In addition, a benchmark and additional experiments are presented to demonstrate the need for independent research on product-centered video-based retrieval. VERD is publicly accessible for academic research and can be downloaded by contacting the author by email.

An ECG Stitching Scheme for Driver Arrhythmia Classification Based on Deep Learning.

This study proposes an electrocardiogram (ECG) signal stitching scheme to detect arrhythmias in drivers during driving. When the ECG is measured through the steering wheel during driving, the data are always exposed to noise caused by vehicle vibrations, bumpy road conditions, and the driver's steering wheel gripping force. The proposed scheme extracts stable ECG signals and transforms them into full 10 s ECG signals to classify arrhythmias using convolutional neural networks (CNN). Before the ECG stitching algorithm is applied, data preprocessing is performed. To extract the cycle from the collected ECG data, the R peaks are found and the TP interval segmentation is applied. An abnormal P peak is very difficult to find. Therefore, this study also introduces a P peak estimation method. Finally, 4 × 2.5 s ECG segments are collected. To classify arrhythmias with stitched ECG data, each time series' ECG signal is transformed via the continuous wavelet transform (CWT) and short-time Fourier transform (STFT), and transfer learning is performed for classification using CNNs. Finally, the parameters of the networks that provide the best performance are investigated. According to the classification accuracy, GoogleNet with the CWT image set shows the best results. The classification accuracy is 82.39% for the stitched ECG data, while it is 88.99% for the original ECG data.

UPLC-QTOFMS based metabolomics followed by stepwise partial least square-discriminant analysis (PLS-DA) explore the possible relation between the variations in secondary metabolites and the phylogenetic divergences of the genus Panax.

Phylogenetic and metabolomic approaches have long been employed to study evolutionary relationships among plants. Nonetheless, few studies have examined the difference in metabolites within a clade and between clades of the phylogenetic tree. We attempted to relate phylogenetic studies to metabolomics using stepwise partial least squares-discriminant analysis (PLS-DA) for the genus Panax. Samples were analyzed by ultra-performance liquid chromatography-quadrupole time of flight mass spectrometry (UPLC-QTOFMS) to obtain metabolite profiles. Initially, conventional principal component analysis was subsequently applied to the metabolomic data to show the limitations in relating the expression of metabolites to divisions in the phylogenetic tree. Thereafter, we introduced stepwise PLS-DA with optimized scaling methods, which were properly applied according to the branches of the phylogenetic tree of the four species. Our approach highlighted metabolites of interest by elucidating the directions and degrees of metabolic alterations in each clade of the phylogenetic tree. The results revealed the relationship between metabolic changes in the genus Panax and its species' evolutionary adaptations to different climates. We believe our method will be useful to help understand the metabolite-evolution relationship.

Rupture of Very Small Intracranial Aneurysms: Incidence and Clinical Characteristics.

OBJECTIVE: Unruptured intracranial aneurysms are now being detected with increasing frequency in clinical practice. Results of the largest studies, including those of the International Study of Unruptured Intracranial Aneurysms, indicate that surgical and endovascular treatments are rarely justified in small aneurysms. However, we have encountered several cases of rupture of small and very small aneurysms in our clinical practice. This retrospective study analyzed the incidence and clinical characteristics of very small ruptured aneurysms. MATERIALS AND METHODS: A total of 200 patients with aneurysmal subarachnoid hemorrhage between January 2012 and December 2014 were reviewed. Various factors were analyzed, including the aneurysm location and size as well as the associated risk factors. RESULTS: The mean age of patients was 56.31 ± 13.78 (range, 25-89) years, and the male to female ratio was 1:2.1. There were 94 (47%) small-sized (< 5 mm), 91 (45.5%) medium-sized (5-9.9 mm), and 15 large-sized (> 10 mm) aneurysms. Of these, 30 (15%) aneurysms were very small-sized (< 3 mm). The most frequent site of aneurysms was the anterior communicating artery (ACoA). However, the proportion of aneurysms at the ACoA was significantly high in very small aneurysms (53.3%, p = 0.013). Hypertension was a significant risk factor for rupture of very small aneurysms (p < 0.001). CONCLUSION: About half of our cases of ruptured aneurysms involved the rupture of small and very small aneurysms. The most common site of rupture of very small aneurysm was the ACoA. Rupture of small and very small aneurysms is unpredictable, and treatment may be considered in selected high-risk patients according to factors such as young age, ACoA location, and hypertension.