检索结果-内蒙古大学图书馆

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Liu, Caihua Shi, Hongyang He, Xinyu Civil Aviat Univ China Coll Comp Sci & Technol Tianjin 300300 Peoples R China CAAC Key Lab Intelligent Airport Theory & Syst Tianjin 300300 Peoples R China Nankai Univ Coll Comp Sci Tianjin 300350 Peoples R China

ISBN: (纸本)9789819985456;9789819985463

The complex architecture and high training cost of Vision Transformers (ViTs) have prompted the exploration of post-training quantization (PTQ). However, introducing previous PTQ into ViTs performed worse because the activation values after processing by the softmax and GELU functions were extremely unbalanced distributed and not the common Gaussian distribution. To solve this problem, we propose a fine-grained ViT quantization method to fit this special distribution and reduce the quantization error of the activation values. We also design an adaptive piecewise point search algorithm that can automatically find the optimal piecewise point. Both the piecewise point and its search process are in the form of a power of two, making it possible to be implemented on general-purpose hardware with a simple shift operation. Experiments show that the quantization algorithm requires only 32 calibration images and achieves nearly lossless prediction accuracy in the classification task of ImageNet dataset. (The accuracy degradation for 8-bit quantization does not exceed 0.45%, and the average degradation is 0.17%).

关键词： Vision transformer quantization Piecewise quantization Post-training quantization adaptive search algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Decision Support Method for Charge Batch Planning of Steelmaking-Continuous Casting under Lagrangian Framework 21st

Research on Decision Support Method for Charge Batch Plannin...

引用

21st IFAC World Congress on Automatic Control - Meeting Societal Challenges

作者： Sun, Liangliang Yu, Yaqian Li, Congxin Cloete, Duncan Stephen Bai, Song Shenyang Jianzhu Univ Sch Informat & Control Engn Shenyang Peoples R China

Charge batch planning is the bottleneck of production management planning in iron and steelmaking enterprises. The optimization of the charge batch planning process will directly influence the iron and steelmaking cost, production and energy consumption. In this paper, an effective mathematical model based on multi-objective weighting method is built up to describe the multi-performance indexes and the multi-constraints;an efficiency adaptive search algorithm based on linear augmented Lagrangian relaxation framework is proposed to alleviate the problem of sawtooth oscillation when the traditional Lagrangian algorithm searches within the feasible domain. The strategy proposed in this paper is verified based on the background of the actual steelmaking and continuous casting management process in China steelmaking plant. The optimization results guarantee the solution quality and speed of charge batch planning of steelmaking-continuous casting. Copyright (C) 2020 The Authors.

关键词： charge batch planning steelmaking and continuous casting production Lagrangian relaxation algorithm adaptive search algorithm

来源：评论

学校读者我要写书评

暂无评论

A collaborative control protocol for agricultural robot routing with online adaptation

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2019年 135卷 456-466页

作者： Dusadeerungsikul, Puwadol Oak Nof, Shimon Y. Purdue Univ PRISM Ctr W Lafayette IN 47907 USA Purdue Univ Sch Ind Engn W Lafayette IN 47907 USA

Stress in crops is one of the major concerns in precision agriculture because it indicates the emergence of disease and damage in plants. Detecting the stress condition of a plant early is critical. A system that can monitor the condition of plants is a desirable solution. In this work, Collaborative Control Theory is utilized to construct a new system, ARS (agricultural robotic system) which synchronizes humans, a mobile robot, and a variable set of sensors to effectively perform the monitoring and detection tasks. A key protocol for that system, which combines routing algorithm, adaptive search algorithm, and collaboration control framework has been developed and validated, and is presented in this article. By using greenhouse as a case study structure, the protocol routes a robot to visit the sampled locations by using a genetic algorithm. In addition, the search algorithm can be guided by the predictive characteristics of the crops' stress, which can spread to other plants according to sunlight, airflow direction, and other known conditions. Based on simulation experiments, the results indicate with statistical significance that (1) the routing algorithm increases the number of successful detections of existing stressed plants by 45.77% compared to monitoring without this routing algorithm. (2) The adaptive search algorithm improves the number of successful detections of stressed plants by 71.88% compared to a system without the adaptive search algorithm. (3) The new protocol developed in this research yields the highest overall robotic efficiency, compared with a system without collaborative control framework.

关键词： Collaborative control theory Collaboration Greenhouse Traveling salesmen problem Sensors adaptive search algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Decision Support Method for Charge Batch Planning of Steelmaking-Continuous Casting under Lagrangian Framework

引用

IFAC-PapersOnLine 2020年第2期53卷 11138-11143页

作者： Liangliang Sun Yaqian Yu Congxin Li Duncan Stephen Cloete Song Bai School of Information and Control Engineering Shenyang Jianzhu University Shenyang China

Charge batch planning is the bottleneck of production management planning in iron and steelmaking enterprises. The optimization of the charge batch planning process will directly influence the iron and steelmaking cost, production and energy consumption. In this paper, an effective mathematical model based on multi-objective weighting method is built up to describe the multi-performance indexes and the multi-constraints; an efficiency adaptive search algorithm based on linear augmented Lagrangian relaxation framework is proposed to alleviate the problem of sawtooth oscillation when the traditional Lagrangian algorithm searches within the feasible domain. The strategy proposed in this paper is verified based on the background of the actual steelmaking and continuous casting management process in China steelmaking plant. The optimization results guarantee the solution quality and speed of charge batch planning of steelmaking-continuous casting.

关键词： charge batch planning steelmaking continuous casting production Lagrangian relaxation algorithm adaptive search algorithm

来源：评论

学校读者我要写书评

暂无评论

Fast adaptive motion estimation algorithm and its efficient VLSI system for high definition videos

引用

EXPERT SYSTEMS WITH APPLICATIONS 2018年 101卷 159-175页

作者： Mukherjee, Rohan Saha, Priyabrata Chakrabarti, Indrajit Dutta, Pranab Kumar Ray, Ajoy Kumar Indian Inst Kharagpur Dept Elect & Elect Commun Engn Kharagpur 721302 W Bengal India Indian Inst Kharagpur Dept Elect Engn Kharagpur 721302 W Bengal India

Motion estimation (ME) plays an important part in the functioning of the video codec by identifying and reducing the temporal redundancies in between successive frames of a video sequence. Block matching algorithm (BMA) has been accepted as one of the finest approaches for motion estimation due to its efficiency and ease of implementation. This paper presents a new and improved iterative and adaptive search strategy for block-based motion estimation along with its efficient hardware implementation. Since it is expected that there will be more demand for streaming video services on mobile devices, designing fine tuning algorithm with dedicated efficient hardware would provide significant benefits. The present motion estimation algorithm is adaptive in nature that takes into consideration the motion content of the current frame while predicting the motion vector. The adaptive nature of the search eases the complexity of motion estimation and the algorithm makes use of the correlation present among the motion vectors of the neighboring blocks to lower the number of search position. Traditionally, such adaptive algorithms are executed by CPU cores running a software stack. Since software involves a significant amount of overheads like fetching into cache, branches, stalls etc., the efficiency of the proposed algorithm can be overshadowed by the hardware platform. To avoid this, compact hardware architecture was developed which stands ahead of other existing architectures as shown in comparison. The VLSI design for the proposed algorithm presented in this work deals with the generation of the adaptive search pattern and use of interleaved memory organization fasten the operational speed. A profitable data re-use scheme and involvement of minimum processing elements required for parallelization reduce the on-chip area. Working at a frequency of 243 MHz, the proposed design can process 66 720p HD (1280 x 720) frames in one second consuming an area of 38.2 K gate equivalent

关键词： adaptive search algorithm Fast motion estimation VLSI architecture Novel memory organization Data re-use

来源：评论

学校读者我要写书评

暂无评论

Chaotic Kbest Gravitational search algorithm (CKGSA) 9

Chaotic Kbest Gravitational Search Algorithm (CKGSA)

引用

9th International Conference on Contemporary Computing (IC3)

作者： Mittal, Himanshu Pal, Raju Kulhari, Ankur Saraswat, Mukesh Jaypee Inst Informat Technol Noida India

ISBN: (纸本)9781509032518

Gravitational search algorithm is a popular adaptive search algorithm among nature-inspired algorithms and has been successfully used for optimizing many real-world problems. Gravitational search algorithm uses the law of Newton gravity for finding the optimal solution. The performance of gravitational search algorithm is controlled by exploration and exploitation capabilities and Kbest is one of its parameters that controls this trade-off. In this paper, a novel chaotic Kbest gravitational search algorithm has been proposed that uses the chaotic model in Kbest to balance the exploration and exploitation non-linearly. The proposed algorithm shows better convergence rate at later iterations with high precision and does not trap into local optima. The experimental results validate that the proposed algorithm outperforms.

关键词： Gravitational search algorithm Chaotic Kbest adaptive search algorithm

来源：评论

学校读者我要写书评

暂无评论

Ultimately accurate SRAF replacement for practical phases using an adaptive search algorithm based on the optimal gradient method

Ultimately accurate SRAF replacement for practical phases us...

引用

Conference on Optical Microlithography XXIII

作者： Maeda, Shimon Nosato, Hirokazu Matsunawa, Tetsuaki Miyairi, Masahiro Nojima, Shigeki Tanaka, Satoshi Sakanashi, Hidenori Murakawa, Masahiro Saito, Tamaki Higuchi, Tetsuya Inoue, Soichi Toshiba Co Ltd Device Proc Dev Ctr Isogo Ku 8 Shinsugita Cho Yokohama Kanagawa 2358522 Japan Tshiba Microelect Corp CAD Dev & Support Dept Kawasaki Kanagawa 210 Japan AIST Informat Technol Res Inst Ibaraki 305 8568 Japan

ISBN: (纸本)9780819480545

SRAF (Sub Resolution Assist Feature) technique has been widely used for DOF enhancement. Below 40nm design node, even in the case of using the SRAF technique, the resolution limit is approached due to the use of hyper NA imaging or low k1 lithography conditions especially for the contact layer. As a result, complex layout patterns or random patterns like logic data or intermediate pitch patterns become increasingly sensitive to photo-resist pattern fidelity. This means that the need for more accurate resolution technique is increasing in order to cope with lithographic patterning fidelity issues in low k1 lithography conditions. To face with these issues, new SRAF technique like model based SRAF using an interference map or inverse lithography technique has been proposed. But these approaches don't have enough assurance for accuracy or performance, because the ideal mask generated by these techniques is lost when switching to a manufacturable mask with Manhattan structures. As a result it might be very hard to put these things into practice and production flow. In this paper, we propose the novel method for extremely accurate SRAF placement using an adaptive search algorithm. In this method, the initial position of SRAF is generated by the traditional SRAF placement such as rule based SRAF, and it is adjusted by adaptive algorithm using the evaluation of lithography simulation. This method has three advantages which are preciseness, efficiency and industrial applicability. That is, firstly, the lithography simulation uses actual computational model considering process window, thus our proposed method can precisely adjust the SRAF positions, and consequently we can acquire the best SRAF positions. Secondly, because our adaptive algorithm is based on optimal gradient method, which is very simple algorithm and rectilinear search, the SRAF positions can be adjusted with high efficiency. Thirdly, our proposed method, which utilizes the traditional SRAF placement, is easy

关键词： SRAF replacement adaptive search algorithm optimal gradient method

来源：评论

学校读者我要写书评

暂无评论

A fast algorithm of gray scale projection

引用

25th Chinese Control Conference

作者： Chai Yun-feng Huang Xian-lin Jie Ming Jin Guang-ming Harbin Inst Technol Harbin 150001 Peoples R China

ISBN: (纸本)9787810778022

The gray scale projection algorithm can detect motion vector of image sequential frames in electronic image stabilization. Three-point adaptive searching algorithm is proposed on the basis of single peak characteristics. The procedures are as follows: through equably selecting three points in searching coverage, judging the variation direction of the correlation curve gradient, the searching parameters will be correspondingly adjusted to obtain the motion vector between frames and then motion filtering and image compensation can be carried out. The algorithm has been demonstrated that the faults of large operation load have been overcome by simulation experiments.

关键词： electronic image stabilization gray projection algorithm adaptive search algorithm

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：