KMS上海科技大学http:///kms.shanghaitech.edu.cn/:802024-03-19T09:01:36Z2024-03-19T09:01:36ZFrame Semantic Role Labeling Using Arbitrary-Order Conditional Random FieldsAi CY(艾超义)Tu KW(屠可伟)http:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3525062024-03-19T03:45:33Z2024-03-19T03:44:50Z题名: Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields
作者: Ai CY(艾超义); Tu KW(屠可伟)
摘要: <p>This paper presents an approach to frame semantic role labeling (FSRL), a task in natural language processing that identifies semantic roles within a text following the theory of frame semantics. Unlike previous approaches which do not adequately model correlations and interactions amongst arguments, we propose arbitrary-order conditional random fields (CRFs) that are capable of modeling full interaction amongst an arbitrary number of arguments of a given predicate. To achieve tractable representation and inference, we apply canonical polyadic decomposition to the arbitrary-order factor in our proposed CRF and utilize mean-field variational inference for approximate inference. We further unfold our iterative inference procedure into a recurrent neural network that is connected to our neural encoder and scorer, enabling end-to-end training and inference. Finally, we also improve our model with several techniques such as span-based scoring and decoding. Our experiments show that our approach achieves state-of-the-art performance in FSRL. </p>2024-03-19T03:44:50Z促进人细胞中γ-珠蛋白产生的方法,编码CRISPR相关蛋白(CAS)、核碱基脱氨酶、单标签RNA(SGRNA)和单指导辅助RNA(HSGRNA)的多核苷酸,以及融合蛋白Jia Chen Bei Yang Li Yang Wenyan Han Shangwu Sun Ying Zhanghttp:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3525052024-03-18T17:00:03Z2024-03-18T17:00:03Z题名: 促进人细胞中γ-珠蛋白产生的方法,编码CRISPR相关蛋白(CAS)、核碱基脱氨酶、单标签RNA(SGRNA)和单指导辅助RNA(HSGRNA)的多核苷酸,以及融合蛋白
作者: Jia Chen Bei Yang Li Yang Wenyan Han Shangwu Sun Ying Zhang2024-03-18T17:00:03ZGuest release from coordination assemblies in the solid stateLiu FZ(刘方梓)http:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3525042024-03-18T07:26:30Z2024-03-18T07:24:15Z题名: Guest release from coordination assemblies in the solid state
作者: Liu FZ(刘方梓)2024-03-18T07:24:15ZEpigenetic regulation in adult neural stem cellsShi,JiajiaWang,zilinWang,zhijunShao,guofengLi,xiajunhttp:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3525032024-03-18T06:01:27Z2024-03-18T05:59:31Z题名: Epigenetic regulation in adult neural stem cells
作者: Shi,Jiajia; Wang,zilin; Wang,zhijun; Shao,guofeng; Li,xiajun
摘要: <p>Neural stem cells (NSCs) exhibit self-renewing and multipotential properties. Adult NSCs are located in two neurogenic regions of adult brain: the ventricularsubventricular zone (V-SVZ) of the lateral ventricle and the subgranular zone of the dentate gyrus in the hippocampus. Maintenance and differentiation of adult NSCs are regulated by both intrinsic and extrinsic signals that may be integrated through expression of some key factors in the adult NSCs. A number of transcription factors have been shown to play essential roles in transcriptional regulation of NSC cell fate transitions in the adult brain. Epigenetic regulators have also emerged as key players in regulation of NSCs, neural progenitor cells and their differentiated progeny via epigenetic modifications including DNA methylation, histone modifications, chromatin remodeling and RNA-mediated transcriptional regulation. This minireview is primarily focused on epigenetic regulations of adult NSCs during adult neurogenesis, in conjunction with transcriptional regulation in these processes.</p>2024-03-18T05:59:31ZTransfer learning of renal cortex segmentation from CT to MRI: facilitated with automatic labelingNi C(倪畅)Mou X(牟欣)Zhang L(张雷)http:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3503022024-03-17T11:31:44Z2024-03-17T11:31:44Z题名: Transfer learning of renal cortex segmentation from CT to MRI: facilitated with automatic labeling
作者: Ni C(倪畅); Mou X(牟欣); Zhang L(张雷)
摘要: <p>Segmentation of renal cortex in MR images is important but challenging. In this study, we proposed to pre-train a ResUNet model with CT images and to use an automatic method for labeling renal cortex for the training data. Such method with transfer learning and automatic labeling performed well in segmenting renal cortex in MR images, with a DICE similarity of 0.85 and volume error of 14%±5%. The proposed method would make labeling of renal cortex for training dataset much more e ciently, and we further con rm the power of transfer learning technique in segmenting renal MR images.</p>2024-03-17T11:31:44ZAccurate exclusion of kidney regions affected by susceptibility artifact in blood oxygenation level-dependent (BOLD) images using deep-learning-based segmentationNi C(倪畅)Mou X(牟欣)Qi HK(齐海坤)Zhang YY(张玉瑶)Zhang L(张雷)http:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3503012024-03-17T11:26:35Z2024-03-17T11:26:35Z题名: Accurate exclusion of kidney regions affected by susceptibility artifact in blood oxygenation level-dependent (BOLD) images using deep-learning-based segmentation
作者: Ni C(倪畅); Mou X(牟欣); Qi HK(齐海坤); Zhang YY(张玉瑶); Zhang L(张雷)
摘要: <p>Susceptibility artifact (SA) is common in renal blood oxygenation level‑dependent (BOLD) images, and including the SA‑affected region could induce much error in renal oxygenation quantification. In this paper, we propose to exclude kidney regions affected by SA in gradient echo images with different echo times (TE), based on a deep‑learning segmentation approach. For kidney segmentation, a ResUNet was trained with 4000 CT images and then tuned with 60 BOLD images. Verified by a Monte Carlo simulation, the presence of SA leads to a bilinear pattern for the segmented area of kidney as function of TE, and the segmented kidney in the image of turning point’s TE would exclude SA‑affected regions. To evaluate the accuracy of excluding SA‑affected regions, we compared the SA‑free segmentations by the proposed method against manual segmentation by an experienced user for BOLD images of 35 subjects, and found DICE of 93.9% ± 3.4%. For 10 kidneys with severe SA, the DICE was 94.5% ± 1.7%, for 14 with moderate SA, 92.8%± 4.7%, and for 46 with mild or no SA, 94.3% ± 3.8%. For the three sub‑groups of kidneys, correction of SA led to a decrease of R2* of 8.5 ± 2.8, 4.7 ± 1.8, and 1.6± 0.9 s−1, respectively. In conclusion, the proposed method is capable of segmenting kidneys in BOLD images and at the same time excluding SA‑affected region in a fully automatic way, therefore can potentially improve both speed and accuracy of the quantification procedure of renal BOLD data.</p>2024-03-17T11:26:35ZPredicting cerebral small vessel disease through retinal scans and demographic data with Bayesian feature selectionChangkai JiJing LiChangde DuBin LvNing WuHongyang LiRui LiYing HuiGuotong XieShoulin WuZhenchang WangHuiguang HeDinggang Shenhttp:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3503002024-03-17T10:41:37Z2024-03-17T10:41:37Z题名: Predicting cerebral small vessel disease through retinal scans and demographic data with Bayesian feature selection
作者: Changkai Ji; Jing Li; Changde Du; Bin Lv; Ning Wu; Hongyang Li; Rui Li; Ying Hui; Guotong Xie; Shoulin Wu; Zhenchang Wang; Huiguang He; Dinggang Shen2024-03-17T10:41:37ZPhotoacoustic imaging plus X: a reviewJiang DH(江道淮)Zhu LY(朱璐瑶)Tong SQ(童尚清)Shen YT(沈雨婷)Gao F(高峰)Gao F(高飞)http:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3502992024-03-17T06:19:19Z2024-03-17T06:19:19Z题名: Photoacoustic imaging plus X: a review
作者: Jiang DH(江道淮); Zhu LY(朱璐瑶); Tong SQ(童尚清); Shen YT(沈雨婷); Gao F(高峰); Gao F(高飞)2024-03-17T06:19:19ZOne-bit Downlink Precoding for Massive MIMO OFDM SystemLiyuan WenHua QianYunbo HuZhicheng DengXiliang Luohttp:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3502982024-03-18T08:50:37Z2024-03-16T07:45:12Z题名: One-bit Downlink Precoding for Massive MIMO OFDM System
作者: Liyuan Wen; Hua Qian; Yunbo Hu; Zhicheng Deng; Xiliang Luo2024-03-16T07:45:12Z一种回收锂离子电池正极材料中金属元素的方法和回收系统管晓飞张旭赵默涵http:///kms.shanghaitech.edu.cn/:80/handle/2MSLDSTB/3502972024-03-15T17:00:13Z2024-03-15T17:00:11Z题名: 一种回收锂离子电池正极材料中金属元素的方法和回收系统
作者: 管晓飞; 张旭; 赵默涵
摘要: 本发明属于电池电极材料回收领域,涉及一种回收锂离子电池正极材料中金属元素的方法和回收系统,所述方法包括以下步骤:通过预处理以获得锂离子电池正极材料;将获得的锂离子电池正极材料与卤化试剂混合,经卤化反应以获得金属卤化物;将获得的金属卤化物与还原性试剂混合,经还原反应以获得金属,回收方法的工艺简单且回收率高。另外本发明的制备方法会产生卤化氢气体,将卤化氢气体回收用于制备卤化试剂,可实现卤化氢的循环利用,减少了卤化氢的消耗。总的来说,本发明提供的回收方法的工艺简单、绿色,具有良好的产业化前景。2024-03-15T17:00:11Z