检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

arXiv

引用

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Regression Network for Dental Implant Position Prediction

arXiv

引用

arXiv 2023年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Chen, Wenting Shen, Linlin Li, Xin 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 Department of Electrical Engineering City University of Hong Kong Hong Kong

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Which year is the hottest or coldest from 2001 to 2012 based on remote sensing data

Which year is the hottest or coldest from 2001 to 2012 based...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： K. B. Mao Y. Ma Z. Y. Zuo F. Wang Y. Q. Jiao X. Y. Shen Q. Liu National Hulunber Grassland Ecosystem Observation and Research Station Chinese Academy of Agricultural Sciences Beijing China Chinese Academy of Agricultural Big Data and Nutrition Hong Kong China State Key Laboratory of Remote Sensing Science Beijing Normal University Beijing China National-Local Joint Engineering Laboratory of Geo-spatial Information Technology Hunan University of Science and Technology Xiangtan China College of Science of China University of Petroleum Beijing China Hydrometeorology and Remote Sensing Laboratory University of Oklahoma Norman Oklahoma

ISBN: (纸本)9781509033331

Increasing extreme weather events has made people confused with which year is the hottest or the coldest in recent years. To answer this question, the region scale and time must be considered. In this study, we calculate global surface temperature by using four surface temperature products at day and night retrieved from MODIS data. The global mean surface temperature is about 14.56° from 2001 to 2012, and the hottest and coldest surface temperatures of the global earth are in 2005 and 2008 in the recent twelve years. The hottest and coldest surface temperatures for the global land are in 2005 and 2001, and in 2010 and 2008 for Ocean. The hottest and coldest surface temperatures for Northern and Southern Hemisphere, Eastern and Western hemisphere, seven continents, and four Ocean are also obtained. The analysis indicates that the change is different in different region. We propose to build a spatial weather-climate model based on gravitational-magmatic change with the solar and the galactic system as its centre to analyze the long-term temperature changes.

关键词： Ocean temperature Sea surface Land surface temperature Temperature distribution Temperature measurement Meteorology

来源：评论

学校读者我要写书评

暂无评论

Ball k-means

arXiv

引用

arXiv 2020年

作者： Xia, Shuyin Peng, Daowan Meng, Deyu Zhang, Changqing Wang, Guoyin Chen, Zizhong Wei, Wei Department of Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China National Engineering Laboratory for Algorithm and Analysis Technologiy on Big Data Xian Jiaotong University Xi'an710049 China College of Intelligence and Computing Tianjin University 300072 China Department of Computer Science and Engineering University of California Riverside 900 University Avenue RiversideCA92521 United States School of Computer Science and Engineering Xi'an University of Technology Xi'an710048 China

This paper presents a novel accelerated exact k-means algorithm called the Ball k-means algorithm, which uses a ball to describe a cluster, focusing on reducing the point-centroid distance computation. The Ball k-means can accurately find the neighbor clusters for each cluster resulting distance computations only between a point and its neighbor clusters centroids instead of all centroids. Moreover, each cluster can be divided into a stable area and an active area, and the later one can be further divided into annulus areas. The assigned cluster of the points in the stable area is not changed in the current iteration while the points in the annulus area will be adjusted within a few neighbor clusters in the current iteration. Also, there are no upper or lower bounds in the proposed Ball k-means. Furthermore, reducing centroid-centroid distance computation between iterations makes it efficient for large k clustering. The fast speed, no extra parameters and simple design of the Ball k-means make it an all-around replacement of the naive k-means algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Global water vapor content and vegetation change analysis based on remote sensing data

Global water vapor content and vegetation change analysis ba...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： K.B. Mao Y. Ma Z. Y. Zuo Y. Q. Jiao F. Wang Q. Liu Z. W. Sun National Hulunber Grassland Ecosystem Observation and Research Station Chinese Academy of Agricultural Sciences Beijing China Chinese Academy of Agricultural Big Data and Nutrition Hong Kong China State Key Laboratory of Remote Sensing Science Beijing Normal University Beijing China College of Science China University of Petroleum Beijing China National-Local Joint Engineering Laboratory of Geo-spatial Information Technology Hunan University of Science and Technology Xiangtan China Space Star Technology Co. Ltd. Beijing China

Water vapor in the Earth's upper atmosphere plays a crucial in the radiative balance, hydrological process, and climate change. Based on the latest MODIS data, this study probes the spatio-temporal variations of global water vapor content in the past decade. It is found that overall the global water vapor concentrations declined over 2003-2012 (b=- 0.0149, R 2 =0.797, p=0.0005). The decreasing trend over the ocean surface (b= -0.017, R 2 =0.824, p=0.0003) is more explicit than over terrestrial surface (b= -0.010, R 2 =0.612, p=0.007), more significant over the Northern Hemisphere (b= -0.0175, R 2 =0.852, p=0.0001) than over the Southern Hemisphere (b= -0.0123, R 2 =0.682, p=0.003). Vegetation cover change is critical for an understanding of the impacts and responses of vegetation to climate change. The global vegetation growth has been analysised from 2001 to 2012. After thorough analysis based on satellite data, we find evidence that the global vegetation change little, and it is increasing slightly in Northern hemisphere while it is deceasing slightly in Southern Hemisphere. For different latitudes, the vegetation is increasing 0.17% every year from 60°N to 70 °N (R 2 =0.47, P>0.013), while the vegetation is decreasing 0.11% every year from 10°N to 10°S (R 2 =0.54, P>0.004). For different continents, the vegetation in South America is decreasing 0.16% every year (R 2 =0.78, P>0.0001) and it is increasing 0.05% every year in Asia (R 2 =0.28, P>0.072) and 0.25% every year in Oceania (R 2 =0.24, P>0.1).

关键词： Vegetation mapping Vegetation MODIS Remote sensing Meteorology Market research Ocean temperature

来源：评论

学校读者我要写书评

暂无评论

Neural multi-objective combinatorial optimization with diversity enhancement 23

Neural multi-objective combinatorial optimization with diver...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jinbiao Chen Zizhen Zhang Zhiguang Cao Yaoxin Wu Yining Ma Te Ye Jiahai Wang School of Computer Science and Engineering Sun Yat-sen University P.R. 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 School of Computer Science and Engineering Sun Yat-sen University P.R. China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University P.R. China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China

关键词：

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：