检索结果-内蒙古大学图书馆

Whole-Genome Sequencing and analysis of the Chinese Herbal Plant Panax notoginseng

学校读者我要写书评

暂无评论

Molecular Plant 2017年第6期10卷 899-902页

作者： Wei Chen Ling Kui Guanghui Zhang Shusheng Zhu Jing Zhang Xiao Wang Min Yang Huichuan Huang Yixiang Liu Yong Wang Yahe Li Lipin Zeng Wen Wang Xiahong He Yang Dong Shengchao Yang Biological Big Data College Yunnan Agricultural University yunnan Research Institute for Local Plateau Agriculture and Industry Kunming 650201 China State Key Laboratory of Genetic Resources and Evolution Kunming Institute of Zoology Chinese Academy of Sciences Kunming 650223 China University of Chinese Academy of Sciences Beijing 100049 China National-Local Joint Engineering Research Center on Germplasm Utilization and Innovation of Chinese Medicinal Materials in Southwest China Yunnan Agricultural University Kunming 650201 China State Key Laboratory for Conservation and Utilization of Bio-Resources in Yunnan Key Laboratory for Agro-biodiversity and Pest Control of Ministry of Education Yunnan Agricultural University Kunming 650201 China NOWBIO Technology Co. Ltd Kunming 650202 China Institute of Panax notoginseng Wenshan University Wenshan 663000 China Longjing Pharmaceutical Co. Ltd Kunming 650228 China Farlong Pharmaceutical Walnut CA 91789 USA College of Life Science Kunming University of Science and Technology Kunming 650504 China

Dear Editor Panax notoginseng （Burk.） F.H. Chen （2n = 2x = 24, common name sanqi or tianql）, belonging to the Araliaceae family, is a slow-growing plant species documented in the ancient Chinese medical literatures for its ability to ameliorate hemostasis and improve blood circulation （Wang et al., 2016）. After decades of pharmacological research, a variety of P. notoginseng-specific secondary metabolites （notably ginsenosides, notoginsenosides and gypenosides） were isolated, identified, and implicated in conferring medicinal properties （Wang et al., 2016）.

关键词： Whole-Genome Sequencing Chinese Herbal Plant Panax notoginseng

A Wavelet-CNN-LSTM Model for Tailings Pond Risk Prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Jun Li, Qing Sun, Yixuan Wang, Wei Li, Linchao Wang, Xuwei Jia, Shengyao Tong, Renyuan National and Local Joint Engineering research center for Disaster Monitoring Technologies and Instruments China Jiliang University Hangzhou310051 China Zhejiang Provincial Key Laboratory of Intelligent Manufacturing Quality Big Data Traceability Analysis and Application China Jiliang University Hangzhou310051 China Zhejiang PeckerAI Technology. Ltd Hangzhou310018 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China

Tailings ponds are places for storing industrial waste. The saturation line is the key factor of quantifying the safety of tailings pond. Existing saturation line time-series prediction methods are mainly based on statistical models or shallow machine learning models. Although these models aim to capture the time dependence of the sequence data, the channel and temporal are even unavailable in principle. In this paper, we presents a two-stage forecasting method, which embeds the channel and temporal attention into a hybrid CNN-LSTM model to predict the saturation line. In the first stage, the discrete wavelet transform (DWT) is applied to capture the refined sequence information. In the second stage, the CNN-LSTM model is utilized to learn the basic spatial and temporal features in the time series. Furthermore, the channel and temporal attention model are embedded into CNN-LSTM model to enhance the feature extracting ability in channel and temporal dimension. Consequently, our proposed model is shown to outperform classic models on five real-world datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

HMOD： An Omics database for Herbal Medicine Plants

学校读者我要写书评

暂无评论

Molecular Plant 2018年第5期11卷 757-759页

作者： Xiao Wang Jiajin Zhang Simei He Yuanni Gao Xiaoqin Ma Yun Gao Guanghui Zhang Ling Kui Wen Wang Ying wang Shengchao Yang Yang Dong State Key Laboratory of Genetic Resources and Evolution Kunming Institute of Zoology Chinese Academy of Sciences Kunming 650223 People's Republic of China Kunming College of Life Science University of Chinese Academy of Sciences Kunming 650204 People's Republic of China School of Information Engineering Yunnan Agricultural University Kunming 650201 People's Republic of China State Key Laboratory of Conservation and Utilization of Bio-resources in Yunnan The Key Laboratory of Medicinal Plant Biology of Yunnan ProvinceNational & Local Joint Engineering Research Center on Germplasms Innovation & Utilization of Chinese Medicinal Materials in Southwest China Yunnan Agricultural University Kunming 650201 People's Republic of China Nowbio Biotech Inc. Kunming 650201 People's Republic of China Province Key Laboratory Biological Big Data College Yunnan Agricultural University Kunming 650201 People's Republic of China Key Laboratory of South China Agricultural Plant Molecular Analysis andGenetic Improvement South China Botanical Garden Chinese Academy of Sciences Guangzhou 510650 People's Republic of China

Dear Editor ,More than 50% of drugs are derived from chemical compounds that have been isolated from various plants （Fabricant and Farnsworth, 2001; Yarnell and Abascal, 2002）. With the development of sequencing technology and synthetic biology, we can obtain molecular information from the transcriptomic and genomic data of plants and then utilize bacteria to synthesize desired chemical compounds （Atanasov et al., 2015; Smanski et al., 2016）. Increasing numbers of researchers have started to publish omics data generated from herbal plants.

关键词：

FPGA-Based Convolution Accelerator and Memristor IP Core for Cooperative Acceleration of the YOLO Network

学校读者我要写书评

暂无评论

FPGA-Based Convolution Accelerator and Memristor IP Core for...

Computer Science, Electronic Information engineering and Intelligent Control technology (CEI), IEEE International Conference on

作者： Aolong Tan Yucheng Yang Shukai Duan Lidan Wang College of Artificial Intelligence Southwest University Chongqing China State Key Laboratory of Intelligent Vehicle Safety Technology National & Local Joint Engineering Research Center of Intelligent Transmission and Control Technology China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing China Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University) Ministry of Education Southwest University Chongqing PR China

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

Object detection technology is widely used in areas such as autonomous driving, drone reconnaissance, smart surveillance and industrial automation, especially in remote or hazardous scenarios where it can improve efficiency and safety. Therefore, the development of a high-precision, low-power acceleration system integrated with low-power hardware is crucial. This paper proposes a collaborative acceleration scheme for the YOLO network based on an FPGA convolution accelerator and simulated memristors, which successfully implements and accelerates the YOLOv4-Tiny model. First, a reconfigurable single-core accelerator operator is designed for various computational operations in the model. Second, taking advantage of the digital device characteristics of memristors and the hardware resources of the FPGA, a memristor simulation IP core is built to exploit its memory characteristics for convolution operations. Through the synergistic effect of the convolution accelerator and the simulated IP core, a hybrid acceleration of the detection model is achieved. The power consumption of the convolution accelerator is only 2.75W, and in testing, the detection time for a single image is 823ms with an average accuracy of over 0.95, achieving high detection performance. This provides an opportunity to explore and research the efficient acceleration of object detection networks with integrated storage and computation.

关键词： YOLO Performance evaluation Power demand Accuracy Convolution Computational modeling Memristors Hardware IP networks Field programmable gate arrays

Multi-Modal Optimization of Stacked Chip Macro-Module Layout Based on Memristor-Inspired Evolutionary Game

学校读者我要写书评

暂无评论

Multi-Modal Optimization of Stacked Chip Macro-Module Layout...

Electronic Information engineering and Computer Communication (EIECC), International Conference on

作者： Kaikai Qiao Ben Ma Mingze Chen Ke Ding Changqing Li Shukai Duan Lidan Wang State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China College of Artificial Intelligence Southwest University Chongqing China National & Local Joint Engineering Research Center of of Intelligent Transmission and Control Technology Chongqing China Chongqing Key Laboratory of Brain-Inspired Computing and Intelligent Chips Chongqing China Key Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University) Ministry of Education Chongqing China

ISBN: (数字)9798331534622

ISBN: (纸本)9798331534639

As the complexity of chip design continues to increase, the stacking of multiple device layers in a three dimension(3D) architecture has emerged as a promising approach, which aims to optimize the placement and interconnections of large function blocks across the vertically-stacked device layers. Due to the complex interactions between layout and design constraints, traditional deterministic optimization often struggle to navigate its multi-modal search landscape effectively. Thus, we creatively propose the memristive evolutionary game: the diverse metal layers engage in a strategic interplay that determines the ownership hierarchy of chip macro modules and the 2D layout of these chip macro modules within each designated metal layer is orchestrated using evolutionary algorithm, which harness the power of game theoretic evolution to seek the optimal solution, balancing the objectives of minimizing layout area and wiring length. Upon comparison with alternative algorithms, the game evolution algorithm introduced in this paper exhibits superior optimization performance.

关键词： Wiring Navigation Layout Stacking Metals Games Evolutionary computation Computer architecture Complexity theory Optimization

High-Performance Sensing: Application of FPGA-based Winograd CNN Accelerator in Electronic Nose Systems

学校读者我要写书评

暂无评论

High-Performance Sensing: Application of FPGA-based Winograd...

Artificial Intelligence and Computer engineering (ICAICE), International Conference on

作者： Aolong Tan Shukai Duan Mingzhe Chen Ke Ding Changqing Li Lidan Wang State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China College of Artificial Intelligence Southwest University Chongqing China National & Local Joint Engineering Research Center of Intelligent Transmission and Control Technology China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing China Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University) Ministry of Education Southwest University Chongqing PR China

ISBN: (数字)9798331528911

ISBN: (纸本)9798331528928

Electronic nose technology has been widely used in various scenarios such as industrial, military, food and environmental, and its recognition accelerator is responsible for completing the detection and identification of gases. Therefore, the application of advanced artificial intelligence algorithms to recognition accelerators is a common practice among researchers nowadays. However, neural networks with high recognition rates tend to have complex structures and a large number of parameters, which exacerbates the difficulty of deployment. To address this challenge, this paper first analyses and processes the detected gas data and proposes a hardware-friendly lightweight gas classification network, and then, based on this network, designs an FPGA-based Winograd CNN accelerator through the study of hardware implementation of Convolutional Neural Networks (CNN). The Winograd algorithm is used to reduce the number of multiplications used in the convolutional operation so as to reduce the consumption of hardware computing resources by the accelerator. Finally, the designed gas classification network is deployed on FPGA to complete the implementation of the recognition acceleration engine in the electronic nose system. The detection and recognition experiments on the laboratory gas dataset demonstrated good performance in terms of 99.5% recognition rate and only 2.94W power consumption of the accelerator, respectively.

关键词： Training Power demand Electronic noses Throughput Hardware Sensors Convolutional neural networks Object recognition Field programmable gate arrays Testing

Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Jinbiao Zhang, Zizhen Cao, Zhiguang Wu, Yaoxin Ma, Yining Ye, Te Wang, Jiahai School of Computer Science and Engineering Sun Yat-sen University China School of Computing and Information Systems Singapore Management University Singapore Department of Industrial Engineering & Innovation Sciences Eindhoven University of Technology Netherlands Department of Industrial Systems Engineering & Management National University of Singapore Singapore Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more solutions in the neighborhood of each subproblem, we present a multiple Pareto optima strategy to sample and preserve desirable solutions. Experimental results on classic MOCO problems show that our NHDE is able to generate a Pareto front with higher diversity, thereby achieving superior overall performance. Moreover, our NHDE is generic and can be applied to different neural methods for MOCO. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

ImplantFormer: Vision Transformer based Implant Position Regression Using Dental CBCT data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Wu, Peixi Shen, Linlin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China The School of Dentistry Shenzhen University Shenzhen China

Implant prosthesis is the most appropriate treatment for dentition defect or dentition loss, which usually involves a surgical guide design process to decide the implant position. However, such design heavily relies on the subjective experiences of dentists. In this paper, a transformer-based Implant Position Regression Network, ImplantFormer, is proposed to automatically predict the implant position based on the oral CBCT data. We creatively propose to predict the implant position using the 2D axial view of the tooth crown area and fit a centerline of the implant to obtain the actual implant position at the tooth root. Convolutional stem and decoder are designed to coarsely extract image features before the operation of patch embedding and integrate multi-level feature maps for robust prediction, respectively. As both long-range relationship and local features are involved, our approach can better represent global information and achieves better location performance. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed ImplantFormer achieves superior performance than existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks