检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pei, Zhiyuan Yan, Jianqi Yan, Jin Yang, Bailing Li, Ziyuan Zhang, Lin Liu, Xin Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology 999078 China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology 999078 China Emerging Technology Innovation and Ventures HSBC Shenzhen518052 China School of Accounting and Finance Beijing Institute of Technology Zhuhai519088 China Department of Mathematics University of Manitoba WinnipegR3T 2N2 Canada

Recently, deep learning in stock prediction has become an important branch. Image-based methods show potential by capturing complex visual patterns and spatial correlations, offering advantages in interpretability over time series models. However, image-based approaches are more prone to overfitting, hindering robust predictive performance. To improve accuracy, this paper proposes a novel method, named Sequence-based Multi-scale Fusion Regression Convolutional Neural Network (SMSFR-CNN), for predicting stock price movements in the China A-share market. Firstly, the historical opening, highest, lowest, closing price, and turnover rate (OHLCT) of stocks are converted into images, separated by weekends, with time information to help the CNN learn the impact of different trading periods. To reduce overfitting, long sequences of stock features are decomposed into multiple time periods, and OHLCT images at different time scales are utilized as inputs, significantly reducing overfitting. Thirdly, in order to overcome the problem that classification labels lose information about the magnitude of stock price changes, we introduce regression labels to help the model capture more latent features of stock price fluctuations. By utilizing CNN to learn sequential features and combining them with image features, we improve the accuracy of stock trend prediction on the A-share market stock dataset. This approach reduces the search space for image features, stabilizes and accelerates the training process. Extensive comparative experiments on 4,454 A-share stocks show that the model achieves 61.15% positive predictive value and 63.37% negative predictive value for the next 5 days, resulting in a total profit of 165.09%. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SIMPLEX: A LEXICAL TEXT SIMPLIFICATION ARCHITECTURE

arXiv

引用

arXiv 2023年

作者： Truică, Ciprian-Octavian Andrei-Ionut, Stan Apostol, Elena-Simona Department of Information Technology Uppsala University Uppsala Sweden Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania

Text simplification (TS) is the process of generating easy-to-understand sentences from a given sentence or piece of text. The aim of TS is to reduce both the lexical (which refers to vocabulary complexity and meaning) and syntactic (which refers to the sentence structure) complexity of a given text or sentence without the loss of meaning or nuance. In this paper, we present SIMPLEX, a novel simplification architecture for generating simplified English sentences. To generate a simplified sentence, the proposed architecture uses either word embeddings (i.e., Word2Vec) and perplexity, or sentence transformers (i.e., BERT, RoBERTa, and GPT2) and cosine similarity. The solution is incorporated into a user-friendly and simple-to-use software. We evaluate our system using two metrics, i.e., SARI, and Perplexity Decrease. Experimentally, we observe that the transformer models outperform the other models in terms of the SARI score. However, in terms of Perplexity, the Word-Embeddings-based models achieve the biggest decrease. Thus, the main contributions of this paper are: (1) We propose a new Word Embedding and Transformer based algorithm for text simplification;(2) We design SIMPLEX - a modular novel text simplification system - that can provide a baseline for further research;and (3) We perform an in-depth analysis of our solution and compare our results with two state-of-the-art models, i.e., LightLS [19] and NTS-w2v [44]. We also make the code publicly available online. © 2023, CC BY-NC-ND.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Organs and Systems Glucose Metabolism Analysis in Different Smoking Groups for Lung Cancer Patients using Total-body PET/CT

Organs and Systems Glucose Metabolism Analysis in Different ...

引用

IEEE Symposium on Nuclear science (NSS/MIC)

作者： H. Wang Z. Huang Y. Wu Z. Liu W. Li M. Wang G.S.P. Mok Z. Hu Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau China Chinese Academy of Sciences Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Shenzhen China Department of Medical Imaging Henan Provincial People’s Hospital & People’s Hospital of Zhengzhou University Zhengzhou China University of Macau Institute of Collaborative Innovation Macau China

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

Smoking history has been an important indicator in lung cancer (LC) screening as it damages lung function. However, whether smoking is harmful to other organs and what abnormalities may occur among various organs have not yet been studied since total-body imaging is not feasible for previous scanners. With the emergence of the total-body PET/CT, we may explore the correlation between abnormal glucose metabolism among various organs and systems for smoking. This work investigates if the smoking intensity plays a role in the metabolic abnormalities among different organs and systems in different smoking groups for LC patients. ${ }^{18} \mathrm{~F}$-FDG PET and CT images from 60 anonymized subjects with 40 LC patients and 20 healthy controls (HCs) are retrospectively recruited and scanned from a uEXPLORER PET/CT. Among LC patients, their smoking intensities were surveyed (non-smokers: light smokers: heavy smokers $=21: 4: 15$). For each scan, 17 regionsof-interests are outlined. To analyze the abnormal metabolism of different smoking groups, we construct individual and group abnormal metabolism networks respectively based on a reference network with HCs. Pearson correlation coefficients between standardized uptake values of each organ pair and system pair are calculated to analyze their connectivities. Results show that more significant abnormal metabolism is observed in smokers as compared to non-smokers. Besides, heavy smokers have a substantially greater proportion of metabolic decline compared with others for lungs, heart, kidneys and esophagus. In addition, the abnormal metabolism connectivity of the lungs-esophagus and lungs-thyroid gland increases significantly along with the increased intensity of smoking, while stronger abnormal metabolism connectivity is also observed between the nervous system and other systems for heavy smokers. The proposed analysis method is feasible for LC patients using total-body FDG PET/CT and has the potential to be applied to other

关键词： Heart Microwave integrated circuits Semiconductor detectors Lung cancer Lung Nervous system Glucose

来源：评论

学校读者我要写书评

暂无评论

DSTFormer: 3D Human Pose Estimation with a Dual-scale Spatial and Temporal Transformer Network

DSTFormer: 3D Human Pose Estimation with a Dual-scale Spatia...

引用

International Conference on advanced Robotics and Mechatronics (ICARM)

作者： Shaokun Zhang Xinde Li Chuanfei Hu Jianping Xu Huaping Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Nanjing Center for Applied Mathematics Nanjing China Southeast University Shenzhen Research Institute Shenzhen China Science and Technology on Information Systems Engineering Laboratory Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Recent transformer-based methods for estimating 3D human pose have gained widespread attention, achieving state-of-the-art results. Previous methods have primarily focused on capturing motion patterns of the human body at a single scale or cascading multiple scales, such as joints, bones, and body-parts. However, they are difficult to simultaneously capture spatial-temporal motion patterns of the human body at different scales due to the complex motion patterns. To address this issue, we propose Dual-scale Spatial and Temporal transFormer (DSTFormer), which can concurrently explore the spatial dependencies and temporal motion patterns of human joints and bones. Additionally, we introduce a Gcn-Spatial Transformer Block (GSTB), which introduces Graph Convolutional Networks (GCN) into transformer to enhance the exploitation of local relationships and global information between adjacent joints or bones. Extensive experiments are conducted on the Human3.6M benchmark dataset, and superior results are reported when comparing to other state-of-the-art methods. More remarkably, our model achieves to-date the best published performance, with P1 errors of 37.9 mm and 15.6 mm, respectively.

关键词： Solid modeling Three-dimensional displays Mechatronics Graph convolutional networks Computational modeling Pose estimation Transformers Bones Joints Robots

来源：评论

学校读者我要写书评

暂无评论

Study on Degradation of Benzo[a]pyrene in Marine Environment by Chlorella vulgaris LH-1 with Heterotrophic Ability 44

Study on Degradation of Benzo[a]pyrene in Marine Environment...

引用

44th AMOP Technical Seminar on Environmental Contamination and Response 2022

作者： Chen, Qingguo Song, Zhao Chen, Yu Zhu, Baikang Liu, Mei Li, Yijing Chen, Zhi Zhejiang Provincial Key Laboratory of Petrochemical Pollution Control Zhejiang Ocean University Zhoushan China School of Marine Science and Technology Zhejiang Ocean University Zhoushan China Department of Building Civil and Environmental Engineering Faculty of Engineering and Computer Sciences Concordia University MontrealQC Canada

After long-term weathering, the most toxic components of residual spilled oil in seawater are polycyclic aromatic hydrocarbons. Benzo[a]pyrene (BaP) is a typical polycyclic aromatic hydrocarbon with high molecular weight, wide distribution, stable properties, and strong carcinogenicity in marine environment. Marine microalgae play an important role in the removal of BaP. Previous studies have mainly focused on the photodegradation of BaP by microalga. However, there are few research on microalgae with heterotrophic ability to degrade BaP. In this study, a microalga, Chlorella vulgaris (C. vulgaris) LH-1, with heterotrophic ability to degrade BaP was studied, the effect of BaP concentration on microalgae growth was explored, and the possible degradation mechanism of BaP by this kind of microalgae was proposed. The results showed that low concentration BaP (-1) had less obvious influence on the growth of C. vulgaris under the mixotrophic condition (with illumination), but a higher concentration BaP (＞ 5 mg L-1) had a significant inhibitory effect on the growth of this microalgae. Under heterotrophic cultivation (without illumination), low concentration BaP (-1) promoted the growth of C. vulgaris LH-1, while high concentration BaP (＞20 mg L-1) led to inhibit the growth of this microalga significantly. The degradation rates of mixotrophic and heterotrophic C. vulgaris LH-1 were 62.56~74.13%, and 52.07~71.67%, respectively, when BaP concentration range from 0.5 to 2 mg/L. Microalgae RNA transcriptome sequencing analysis showed that the gene expression of functional enzyme of C. Vulgaris LH-1 such as phenol 2-monooxygenase activity, protocatechuate 3,4-dioxygenase activity, catechol 1,2-dioxygenase activity, styrene degradation, and benzoate degradation were up-regulated in the process of BaP degradation. Based on the results of metabolites detected by high performance liquid chromatography/ quadruple time-of-flight mass spectrometry (HPLC/ Q-TOF), C. Vulgaris LH-1 may de

关键词： Degradation

来源：评论

学校读者我要写书评

暂无评论

Cooperative Coevolution for Non-Separable Large-Scale Black-Box Optimization: Convergence Analyses and Distributed Accelerations

arXiv

引用

arXiv 2023年

作者： Duan, Qiqi Shao, Chang Zhou, Guochen Yang, Haobin Zhao, Qi Shi, Yuhui Harbin Institute of Technology Heilongjiang Harbin150001 China Faculty of Engineering and Information Technology University of Technology Sydney 15 Broadway Ultimo SydneyNSW2007 Australia Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

Given the ubiquity of non-separable optimization problems in real worlds, in this paper we analyze and extend the large-scale version of the well-known cooperative coevolution (CC), a divide-and-conquer black-box optimization framework, on non-separable functions. First, we reveal empirical reasons of when decomposition-based methods are preferred or not in practice on some non-separable large-scale problems, which have not been clearly pointed out in many previous CC papers. Then, we formalize CC to a continuous-game model via simplification, but without losing its essential property. Different from previous evolutionary game theory for CC, our new model provides a much simpler but useful viewpoint to analyze its convergence, since only the pure Nash equilibrium concept is needed and more general fitness landscapes can be explicitly considered. Based on convergence analyses, we propose a hierarchical decomposition strategy for better generalization, as for any decomposition, there is a risk of getting trapped into a suboptimal Nash equilibrium. Finally, we use powerful distributed computing to accelerate it under the recent multi-level learning framework, which combines the fine-tuning ability from decomposition with the invariance property of CMA-ES. Experiments on a set of high-dimensional test functions validate both its search performance and scalability (w.r.t. CPU cores) on a clustering computing platform with 400 CPU cores. Copyright © 2023, The Authors. All rights reserved.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Experimental verification of group non-membership in optical circuits

引用

Photonics Research 2021年第9期9卷 1745-1751页

作者： KAI SUN ZI-JIAN ZHANG FEI MENG BIN CHENG ZHU CAO JIN-SHI XU MAN-HONG YUNG CHUAN-FENG LI GUANG-CAN GUO CAS Key Laboratory of Quantum Information University of Science and Technology of ChinaHefei 230026China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of ChinaHefei 230026China Department of Physics Southern University of Science and TechnologyShenzhen 518055China Department of Computer Science The University of Hong KongPokfulamHong Kong SARChina Centre for Quantum Software and Information Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydneyNSW 2007Australia Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and TechnologyShanghai 200237China Shenzhen Institute for Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China

The class quantum Merlin–Arthur(QMA),as the quantum analog of nondeterministic polynomial time,contains the decision problems whose YES instance can be verified efficiently with a quantum *** problem of deciding the group non-membership(GNM)of a group element is conjectured to be a member of *** works on the verification of GNM,which still lacks experimental demonstration,required a quantum circuit with O(n~5)group oracle ***,we provide an efficient way to verify GNM problems,in which each quantum circuit only contains O(1)group of oracle calls,and the number of qubits in each circuit is reduced by *** on this protocol,we then experimentally demonstrate the new verification process with a four-element group in an all-optical *** new protocol is validated experimentally by observing a significant completeness-soundness gap between the probabilities of accepting elements in and outside the *** work efficiently simplifies the verification of GNM and is helpful in constructing more quantum protocols based on the near-term quantum devices.

关键词： quantum element polynomial

来源：评论

学校读者我要写书评

暂无评论

ASPR-based Output Feedback control with Virtual PFC for Output Tracking

引用

IFAC-PapersOnLine 2023年第2期56卷 9245-9250页

作者： Kota Akaike Hao Yu Ikuro Mizumoto Tongwen Chen Department of Graduate School of Science and Technology Kumamoto University Kumamoto Japan Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 1H9 Canada Department of Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

Nowadays, the output feedback control method based on the Almost Strictly Positive Real (ASPR) property gets many attentions and has been researched widely. ASPR models can be stabilized by applying simple output feedback control; so the designed controllers have a simple structure. However, the systems have to satisfy quite strict conditions in order to obtain ASPR-ness, although almost all practical systems do not have the ASPR property. Therefore, for relaxing those conditions, the introduction of a Parallel Feedforward Compensator (PFC) has been proposed. This method can render the resulting augmented system ASPR. Up to now, several PFC design methods have been proposed, and one of them is an adaptive PFC design scheme. This technique has a feature that it can design a PFC automatically by utilizing online data. Furthermore, for the purpose of output regulation, the control design methods with an adaptive PFC have been proposed. Unfortunately, however, in almost all schemes, the discussion on the convergence of actual errors has not been conducted. Therefore, in this paper, introducing a virtual PFC model and an auxiliary input for ensuring ASPR-ness, a new ASPR-based output feedback control method is proposed, and the stability analysis and convergence of the actual error are discussed. Finally, the effectiveness of the proposed method is confirmed via numerical simulations.

关键词： Adaptive control Output feedback Output regulation Stability analysis Convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive Muti-Scale Tf-Net for High-Resolution Time-Frequency Representations

SSRN

引用

SSRN 2023年

作者： Chen, Tao Chen, Qiming Zheng, Qian Li, Zhishan Zhang, Ziyi Xie, Lei Su, Hongye State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China DAMO Academy Alibaba Group Hangzhou China College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Michigan 500 S. State Street Ann ArborMI48109 United States

In this paper, a novel adaptive multi-scale time-frequency network (AMTFN) is proposed to provide high-resolution time-frequency representations for nonstationary signals. AMTFN is an end-to-end deep network, which firstly adaptively learns the comprehensive basis functions to produce time-frequency (TF) feature maps through multi-scale 1D convolutional kernels. Then, the channel attention mechanism is embedded into AMTFN to rescale the TF feature maps selectively. Thus, the subsequent residual encoder-decoder block’s energy concentration performance is greatly improved with these rescaled TF feature maps. Besides, this paper designs a new training strategy to elegantly enable the model to pay more attention to the intersections of instantaneous frequencies trajectories. In the end, a series of simulations as well as real-world cases is studied to demonstrated the effectiveness and advantages of the proposed method. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

In Situ Iodide Passivation Toward Efficient CsPbI_(3) Perovskite Quantum Dot Solar Cells

引用

Nano-Micro Letters 2023年第10期15卷 28-39页

作者： Junwei Shi Ben Cohen‑Kleinstein Xuliang Zhang Chenyu Zhao Yong Zhang Xufeng Ling Junjun Guo Doo‑Hyun Ko Baomin Xu Jianyu Yuan Wanli Ma Department of Materials Science and Engineering Southern University of Science and TechnologyShenzhen 518055People’s Republic of China Institute of Functional Nano&Soft Materials(FUNSOM) Soochow University199 Ren‑Ai RoadSuzhou Industrial ParkSuzhou 215123People’s Republic of China Department of Electrical and Computer Engineering University of British Columbia2329 West MallVancouverBC V6T 1Z4Canada Department of Chemistry Sungkyunkwan UniversitySuwon 16419Republic of Korea Jiangsu Key Laboratory of Advanced Negative Carbon Technologies Soochow University199 Ren‑Ai RoadSuzhou Industrial ParkSuzhou 215123People’s Republic of China Jiangsu Key Laboratory for Carbon‑Based Functional Materials&Devices Soochow University199 Ren‑Ai RoadSuzhou Industrial ParkSuzhou 215123People’s Republic of China

All-inorganic CsPbI_3 quantum dots(QDs) have demonstrated promising potential in photovoltaic(PV) applications. However, these colloidal perovskites are vulnerable to the deterioration of surface trap states, leading to a degradation in efficiency and stability. To address these issues, a facile yet effective strategy of introducing hydroiodic acid(HI) into the synthesis procedure is established to achieve high-quality QDs and devices. Through an in-depth experimental analysis, the introduction of HI was found to convert PbI_2 into highly coordinated [PbI_m]~(2-m), enabling control of the nucleation numbers and growth kinetics. Combined optical and structural investigations illustrate that such a synthesis technique is beneficial for achieving enhanced crystallinity and a reduced density of crystallographic defects. Finally, the effect of HI is further reflected on the PV performance. The optimal device demonstrated a significantly improved power conversion efficiency of 15.72% along with enhanced storage stability. This technique illuminates a novel and simple methodology to regulate the formed species during synthesis, shedding light on ofurther understanding solar cell performance, and aiding the design of future novel synthesis protocols for high-performance optoelectronic devices.

关键词： CsPbI_(3)perovskite quantum dots In situ passivation Surface trap states Perovskite solar cell

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：