检索结果-内蒙古大学图书馆

Apple stem/calyx real-time recognition using YOLO-v5 algorithm for fruit automatic loading system

POSTHARVEST BIOLOGY AND TECHNOLOGY 2022年第0期185卷 111808-111808页

作者： Wang, Zhipeng Jin, Luoyi Wang, Shuai Xu, Huirong Zhejiang Univ Coll Biosyst Engn & Food Sci 866 Yuhangtang Rd Hangzhou 310058 Peoples R China Minist Agr Key Lab Site Proc Equipment Agr Prod Beijing Peoples R China

Fruit loading and packaging are still labor-intensive tasks during postharvest commercialization, of which the key issues is to realize the real-time detection and adjustment of fruit posture. However, fruit stem/calyx position is a key structural characteristic for fruit posture and will also affect fruit internal quality detection. In this paper, an image acquisition system based on fruit posture adjustment equipment was set up, and the YOLO-v5 algorithm based on deep learning was used to study the real-time recognition of stem/calyx of apples. First, hyperparameters were determined, and the training method of transfer learning was used to obtain better detection performance;then the networks with different widths and depths were trained to find the best baseline detection net;finally, the YOLO-v5 algorithm was optimized for this task by using detection head searching, layer pruning and channel pruning. The results showed that under the same setting conditions, YOLO-v5s had a more superior usability and could be selected as the baseline network considering detection performance, model weight size, and detection speed. After optimization, the complexity of the algorithm was further reduced. The model parameters and weight volume were decreased by about 71 %, while mean Average Precision (mAP) and F1-score (F1) were only decreased by 1.57 % and 2.52 %, respectively. The optimized algorithm could achieve real-time detection under CPU condition at a speed of 25.51 frames per second (FPS). In comparison with other deep learning target detection algorithms, the algorithm used in this paper was similar to other lightweight networks in complexity. Its mAP and F1 were 0.880 and 0.851, respectively. This was better than other one-stage object detection algorithms in detection ability, only lower than that of Faster R-CNN. The optimized YOLO-v5s achieved 93.89 % accuracy in fruit stem/calyx detection for different cultivars of apples. This research could lay the foundation f

关键词： Apple stem calyx Real-time recognition YOLO-v5 algorithmic optimization

来源：评论

学校读者我要写书评

暂无评论

algorithmic formulation of clay and sand pipe-soil interaction models for on-bottom stability analysis

引用

MARINE STRUCTURES 2021年 78卷 102985-102985页

作者： Longva, Vegard Ji, Guomin Saevik, Svein Ye, Naiquan Gjosteen, Janne K. O. Giertsen, Egil Wang, Yanbin SINTEF Ocean Postbox 4762 Torgarden N-7465 Trondheim Norway Norwegian Univ Sci & Technol Dept Mfg & Civil Engn N-2821 Gjovik Norway Norwegian Univ Sci & Technol Dept Marine Technol N-7491 Trondheim Norway China Univ Petr 18 Fuxue Rd Beijing 102249 Peoples R China

This paper presents a new algorithmic formulation of the clay and sand pipe-soil interaction models recommended by the DNV-RP-F109 code for dynamic on-bottom stability analysis of submarine pipelines. The pipe-soil force update algorithm is formulated within the framework of computational elasto-plasticity and applies Backward-Euler integration to ensure stability and robustness for large time step sizes. algorithmic optimization techniques are developed by utilizing a closed-form solution and subincrementation. A numerical verification study covering full cyclic displacement ranges of a 12 inch pipeline is presented. The new formulation is shown to increase the time step size by a factor of up to 50 compared to commercial software tools for on-bottom stability analysis. This achievement will be particularly beneficial for long-duration 3D nonlinear time domain on-bottom stability analysis.

关键词： Pipe-soil interaction On-bottom stability Elasto-plastic algorithmic optimization Backward-Euler update algorithm

来源：评论

学校读者我要写书评

暂无评论

Generalized approach for radiotherapy treatment planning by optimizing projected health outcome: preliminary results for prostate radiotherapy patients

引用

PHYSICS IN MEDICINE AND BIOLOGY 2021年第6期66卷 065007页

作者： Wilson, Lydia J. Newhauser, Wayne D. Louisiana State Univ Dept Phys & Astron Baton Rouge LA 70803 USA Mary Bird Perkins Canc Ctr 4950 Essen Lane Baton Rouge LA 70809 USA

Research in cancer care increasingly focuses on survivorship issues, e.g. managing disease- and treatment-related morbidity and mortality occurring during and after treatment. This necessitates innovative approaches that consider treatment side effects in addition to tumor cure. Current treatment-planning methods rely on constrained iterative optimization of dose distributions as a surrogate for health outcomes. The goal of this study was to develop a generally applicable method to directly optimize projected health outcomes. We developed an outcome-based objective function to guide selection of the number, angle, and relative fluence weight of photon and proton radiotherapy beams in a sample of ten prostate-cancer patients by optimizing the projected health outcome. We tested whether outcome-optimized radiotherapy (OORT) improved the projected longitudinal outcome compared to dose-optimized radiotherapy (DORT) first for a statistically significant majority of patients, then for each individual patient. We assessed whether the results were influenced by the selection of treatment modality, late-risk model, or host factors. The results of this study revealed that OORT was superior to DORT. Namely, OORT maintained or improved the projected health outcome of photon- and proton-therapy treatment plans for all ten patients compared to DORT. Furthermore, the results were qualitatively similar across three treatment modalities, six late-risk models, and 10 patients. The major finding of this work was that it is feasible to directly optimize the longitudinal (i.e. long- and short-term) health outcomes associated with the total (i.e. therapeutic and stray) absorbed dose in all of the tissues (i.e. healthy and diseased) in individual patients. This approach enables consideration of arbitrary treatment factors, host factors, health endpoints, and times of relevance to cancer survivorship. It also provides a simpler, more direct approach to realizing the full beneficial potenti

关键词： biological optimization treatment planning prostate radiotherapy proton therapy photon therapy algorithmic optimization

来源：评论

学校读者我要写书评

暂无评论

Emotional tendency of online legal course review texts based on SVM algorithm and network data acquisition

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2019年第5期37卷 6253-6263页

作者： Yuan, Xiaoyi Xian Peihua Univ Sch Accounting & Finance Xian 710125 Shaanxi Peoples R China

The lack of effective evaluation of online education is a worldwide malpractice, and it is impossible to help students improve the correctness of online learning choices through existing reviews. Based on the current mainstream sentiment lexicon and text sentiment analysis, the authors use machine learning method to analyze the sentiment orientation of the legal course review text, through method that combines PMI and SVM. At the same time, this paper uses LibSVM tool to train and predict data, collect and pre-process data through network data collection, and, based on traditional algorithms, propose improved experimental scheme based on their respective advantages and disadvantages. In addition, the model proposed in this study is used to classify and process the emotional text, and the two methods are combined to obtain the final result. Finally, this paper combines experiments to analyze the performance of the comprehensive model proposed in this study. The research shows that the classification effect of the text sentiment analysis of model is good, it can be applied to practice, and it can provide theoretical reference for subsequent related research.

关键词： Support vector machine algorithmic optimization online course data network

来源：评论

学校读者我要写书评

暂无评论

Hardware Accelerated Image Processing on an FPGA-SoC Based Vision System for Closed Loop Monitoring and Additive Manufacturing Process Control 12th

Hardware Accelerated Image Processing on an FPGA-SoC Based V...

引用

12th International Conference on Computer Vision Systems (ICVS)

作者： Scharf, Dietmar Le Viet, Bach Thi Bich Hoa Le Rechenberg, Janine Tschierschke, Stefan Vogl, Ernst Vandone, Ambra Giardini, Mattia Ramteid GmbH Amberg Germany Univ Appl Sci SUPSI Manno Switzerland

ISBN: (纸本)9783030349950;9783030349943

In many industrial sectors such as aeronautics, power generation, oil & gas, complex metal parts especially the critical ones are constructed and manufactured for a very long lifespan (more than 10 years). 4D Hybrid, an EU research project develops a new concept of hybrid additive manufacturing (AM) modules to ensure first time right production. To achieve that, the in-line process monitoring activity can be persistently realized by a complex sensing and vision system mounted on the equipment to ensure that the process responds to nominal operating conditions. This paper presents concepts and design of the vision system for process monitoring activities with hardware accelerated image processing by using camera hardware based on SoC FPGA devices, a hybrid of FPGA and ARM-based Cortex-A9 dual core CPU.

关键词： Image processing FPGA SoC (System on Chip) Machine vision Additive manufacturing algorithmic optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Automated Trading Systems

Optimizing Automated Trading Systems

引用

International Conference on Digital Science (DSIC)

作者： Bigiotti, Alessandro Navarra, Alfredo Univ Perugia Dept Math & Comp Sci Perugia Italy

ISBN: (纸本)9783030023515;9783030023508

In 2016, more than the 80% of transactions in the Forex market (where the world's currencies trade) have been directed by robots. The design of profitable automatic trading systems is becoming a challenging process. This requires a strong synergy of economists and computer scientists. Our aim is to provide an optimization framework for trading systems that starting from a generic strategy, enhances its performances by exploiting mathematical constraints. Moreover, the growth of new markets requires suitable solutions integrating computer science tools with economic analysis. In this work, we mainly refer to an emerging market known as Binary Options. Starting from basic strategies used every day in the stock markets by professional traders, we show how optimization issues enhance the outcoming performances. Tests on the optimized algorithms are conducted on both historical and real time data.

关键词： Trading system algorithmic optimization Binary Options

来源：评论

学校读者我要写书评

暂无评论

A Framework for Generating High Throughput CNN Implementations on FPGAs 18

A Framework for Generating High Throughput CNN Implementatio...

引用

ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)

作者： Zeng, Hanqing Chen, Ren Zhang, Chi Prasanna, Viktor Univ Southern Calif Ming Hsieh Dept Elect Engn Los Angeles CA 90007 USA Univ Southern Calif Dept Comp Sci Los Angeles CA 90007 USA

ISBN: (纸本)9781450356145

We propose a framework to generate highly efficient accelerators for inferencing on FPGAs. Our framework consists of multiple algorithmic optimizations for computation complexity and communication volume reduction, a mapping methodology for efficient resource utilization, and a tool for automatic Veri log generation. The algorithmic optimizations improve throughput of frequency domain convolution so as to satisfy a given set of hardware constraints. While the Overlap-and-Add (OaA) technique has been known, it performs "wasted" computation at the edges. We propose a novel Concatenate-and-Pad (CaP) technique, which improves OaA significantly by reducing the "wasted" computation on the padded pixels. The proposed CaP used in conjunction with OaA enables us to choose a fixed FFT size at design time, and achieve low computation complexity for layers with various image sizes and kernel window sizes. We also develop a novel frequency domain loop tiling technique to further boost the throughput by improving data reuse. Our mapping methodology optimizes the architecture for the target device by fast design space exploration. We quantitatively categorize FPGAs by capturing their DSP resources, on-chip memory size and external memory bandwidth into a device coefficient. We identify the optimal architectural parameters based on the tradeoff between computation and communication cost. Our framework includes a tool to automatically generate fully synthesizable Verilog. We demonstrate the framework by generating high throughput accelerators for state-of-the-art CNN models on Intel HARP heterogeneous platform. Using our framework, we achieve throughput of 780.6 GOPS, 669.1 GOPS and 552.1 GOPS for AlexNet, VGG16 and FCN-16s respectively. These correspond to 6.8x (AlexNet) and 4.9x (VGG16) improvement compared with the state-of-the-art implementations.

关键词： Convolutional Neural Networks algorithmic optimization Hard-ware Mapping Software-Hardware Co-design FPGA

来源：评论

学校读者我要写书评

暂无评论

Autotuning algorithmic Choice for Input Sensitivity 15

Autotuning Algorithmic Choice for Input Sensitivity

引用

36th ACM SIGPLAN Conference on Programming Language Design and Implementation

作者： Ding, Yufei Ansel, Jason Veeramachaneni, Kalyan Shen, Xipeng O'Reilly, Una-May Amarasinghe, Saman N Carolina State Univ Raleigh NC 27695 USA MIT Cambridge MA 02139 USA

ISBN: (纸本)9781450334686

A daunting challenge faced by program performance autotuning is input sensitivity, where the best autotuned configuration may vary with different input sets. This paper presents a novel two-level input learning algorithm to tackle the challenge for an important class of autotuning problems, algorithmic autotuning. The new approach uses a two-level input clustering method to automatically refine input grouping, feature selection, and classifier construction. Its design solves a series of open issues that are particularly essential to algorithmic autotuning, including the enormous optimization space, complex influence by deep input features, high cost in feature extraction, and variable accuracy of algorithmic choices. Experimental results show that the new solution yields up to a 3x speedup over using a single configuration for all inputs, and a 34x speedup over a traditional one-level method for addressing input sensitivity in program optimizations.

关键词： Algorithms Languages Performance Petabricks Autotuning algorithmic optimization Input Adaptive Input Sensitivity Two-level Input Learning

来源：评论

学校读者我要写书评

暂无评论

The Group Formation Problem: An algorithmic Approach to Learning Group Formation

The Group Formation Problem: An Algorithmic Approach to Lear...

引用

9th European Conference on Technology Enhanced Learning (EC-TEL)

作者： Konert, Johannes Burlak, Dmitrij Steinmetz, Ralf Tech Univ Darmstadt Darmstadt Germany

ISBN: (纸本)9783319112008;9783319111995

Fostering knowledge exchange among peers is important for learners' motivation, achievement of learning goals as well as improvement of problem solving competency. Still, the positive effects of such an exchange depend strongly on the suitability of the selected peers in a group. A comparison of existing algorithmic solutions applicable for E-learning and CSCL scenarios reveals limited support for requirements derived from related work in pedagogical psychology. Therefore, the GroupAL algorithm is proposed. It supports the use of criteria that are either expected to be matched homogeneous or heterogeneous among participants while aiming for equally good group formation for all groups. A normed metric allows for comparison of different group formations and is robust against variations. Finally, the evaluation reveals the advantages and widespread applicability of GroupAL. Compared to existing solutions, it achieves a better group formation quality under the chosen conditions.

关键词： Learning Group Formation algorithmic optimization Matching CSCL

来源：评论

学校读者我要写书评

暂无评论

A Novel Space Partitioning Algorithm to Improve Current Practices in Facility Placement

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS 2012年第5期42卷 1194-1205页

作者： Jimenez, Tamara Mikler, Armin R. Tiwari, Chetan Univ N Texas Ctr Computat Epidemiol & Response Anal Denton TX 76207 USA

In the presence of naturally occurring and man-made public health threats, the feasibility of regional bio-emergency contingency plans plays a crucial role in the mitigation of such emergencies. While the analysis of in-place response scenarios provides a measure of quality for a given plan, it involves human judgment to identify improvements in plans that are otherwise likely to fail. Since resource constraints and government mandates limit the availability of service provided in case of an emergency, computational techniques can determine optimal locations for providing emergency response assuming that the uniform distribution of demand across homogeneous resources will yield an optimal service outcome. This paper presents an algorithm that recursively partitions the geographic space into subregions while equally distributing the population across the partitions. For this method, we have proven the existence of an upper bound on the deviation from the optimal population size for subregions.

关键词： Algorithm algorithmic optimization epidemics optimization pandemics and biological threats public health preparedness response analysis

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：