检索结果-内蒙古大学图书馆

A study on robot-human system with consideration of individual preferences (1st report, construction of a planar-two-degrees-of-freedom robot system for handing over motion based on image processing)

引用

JSME international JOURNAL SERIES C-MECHANICAL SYstEMS machine ELEMENTS AND MANUFACTURING 2003年第3期46卷 1075-1083页

作者： Jindai, M Shibata, S Yamamoto, T Shimizu, A Ehime Univ Fac Engn Matsuyama Ehime 7908577 Japan Ehime Univ Grad Sch Sci & Engn Matsuyama Ehime 7908577 Japan

We construct a handing over robot system with consideration of individual preferences. In this robot system, a human (cooperator) can adjust motion characteristics of planar two-degrees-of-freedom robot to satisfy his or her individual preferences. The robot recognizes the shape of the cooperator's hand as the order using image processing. Then, the robot changes the motion characteristics, such as the maximum velocity, the position of the velocity peak, the handing over position and the initial position, according to the cooperator's order (that is preference). By accomplishing the adjustments, the handing over motion of the robot will become the most comfortable for the cooperator. Furthermore, this proposed robot system uses a bell-shaped velocity pattern based on the minimum jerk model, which can reproduce the point-to-point motion of human hands. Therefore, the motion of this robot becomes similar to human's hand motion, and a more human friendly robot can be realized.

关键词： robot-human system individual preference man-machine interface image processing handing over motion bell-shaped velocity pattern

来源：评论

学校读者我要写书评

暂无评论

Efficient Segmentation of Breast Cancer CT images: A Multi-Threshold image Segmentation Method Based on learning Search Algorithm 24

Efficient Segmentation of Breast Cancer CT Images: A Multi-T...

引用

1st international conference on image processing machine learning and pattern recognition

作者： Chen, Jun Wei, Qinshao Dong, Shanshan Qin, Chunlin Pan, Tingjiang Lu, Zenghui Qu, Chiwen Youjiang Med Univ Natl Sch Humanities & Management Baise Peoples R China Youjiang Med Univ Natl Sch Med Imaging Baise Peoples R China Youjiang Med Univ Natl Sch Languages & Cultures Baise Peoples R China Baise Hlth Meteorol Integrat Innovat Ctr Baise Peoples R China

ISBN: (纸本)9798400707032

Early diagnosis of breast cancer is crucial for improving patient survival rates, with medical imaging technology playing a key role. Traditional image segmentation methods suffer from limitations such as sensitivity to thresholds and a tendency to become trapped in local optima. Metaheuristic algorithms (MAs) offer an effective strategy to address these issues. This study introduces a novel optimization algorithm-learning Search Algorithm (LSA)-that simulates human learning behaviors, including historical experience, social role modeling, and proactive learning, to optimize multi-threshold image segmentation. The LSA employs dynamic adaptive control parameters during the global search and local exploitation phases, enhancing segmentation accuracy and convergence speed. In the application of breast cancer CT image segmentation, the LSA outperforms existing advanced algorithms, providing higher quality solutions. This research not only enriches the repertoire of image segmentation algorithms but also provides new technical support for the early diagnosis and treatment of breast cancer.

关键词： Breast Cancer Multi-Threshold image Segmentation learning Search Algorithm

来源：评论

学校读者我要写书评

暂无评论

An FPGA-Accelerated Approach to Direct Waveform processing for Low-Power Keyword Spotting 24

An FPGA-Accelerated Approach to Direct Waveform Processing f...

引用

1st international conference on image processing machine learning and pattern recognition

作者： Yang, Yucheng Duan, Shukai Wang, Lidan Southwest Univ Coll Artificial Intelligence Chongqing Peoples R China

ISBN: (纸本)9798400707032

Natural language processing is typically high-power-consuming, hence we require a gating switch to activate the natural language processing system only when needed. The gating switch is the keyword-spotting system, which is always kept in an open state;therefore, it is essential to ensure the system operates with low power consumption. To address this issue, this paper firstly introduces a convolutional algorithm that directly convert voice signals into Mel-frequency cepstral coefficients features. Compared to traditional feature extractors, this algorithm significantly reduces computational load, thereby lowering power consumption. Subsequently, in order to further reduce computational load and lower power consumption, we introduced a classifier with weight binarization. To enhance the accuracy of this classifier, a two-step distillation method was proposed. Finally, this article presents an FPGA-based hardware accelerator that implements accelerated inference computation for a KWS engine within an FPGA. Compared to a high-performance general-purpose processor (Intel Core i5-12400F), the FPGA-based pattern recognition engine hardware accelerator achieves a speedup of 28.6 times, while its power consumption is only 4.2% of that of the i5-12400F.

关键词： FPGA accelerator keyword-spotting

来源：评论

学校读者我要写书评

暂无评论

CBLMA: A Hybrid Model for Robust Signal Classification with Convolutional and Bidirectional LstM Layers 24

CBLMA: A Hybrid Model for Robust Signal Classification with ...

引用

1st international conference on image processing machine learning and pattern recognition

作者： Feng, Xiaoxu Jianzhu Univ Urban Construct Coll Shenyang Peoples R China

ISBN: (纸本)9798400707032

The accurate categorisation of modulation schemes under different signal-to-noise ratios (SNRs) has become a significant and challenging issue in the context of rapidly evolving and increasingly complex contemporary communication systems. This paper addresses this significant challenge by proposing a novel and sophisticated hybrid model, namely, Convolutional Bidirectional Long Short-Term Memory (CBLMA) with Multiple Heads of Attention. The methodology adopted in this research project involves the seamless and harmonious integration of convolutional layers for the extraction of detailed spatial features, bi-directional LstM layers dedicated to the capture of complex temporal dependencies, and a multi-head attention mechanism that plays a key role in the dynamic and accurate adjustment of focus. The experimental results clearly illustrate the model's exceptional performance in classifying simple modulation schemes. Furthermore, it demonstrates considerable resilience and adaptability in addressing intricate modulation scenarios and high-noise conditions. It is notable that the CBLMA model offers a highly practical and efficient solution to the signal classification task while simultaneously facilitating the exploration of a multitude of promising avenues for a diverse array of applications within the expansive domain of communication systems.

关键词： Modulation Classification Deep learning Convolutional Neural Networks (CNN) Bidirectional Long Short-Term Memory (BiLstM) Multi-Head Attention Mechanism Signal-to-Noise Ratio (SNR)

来源：评论

学校读者我要写书评

暂无评论

2022 1st international conference on Artificial Intelligence Trends and pattern recognition, ICAITPR 2022

2022 1st International Conference on Artificial Intelligence...

引用

1st international conference on Artificial Intelligence Trends and pattern recognition, ICAITPR 2022

ISBN: (纸本)9781665425216

The proceedings contain 49 papers. The topics discussed include: analysis of customer reviews using deep neural network;a comparative investigation on the use of machine learning techniques for currency authentication;a diagnostic survey on sybil attack on cloud and assert possibilities in risk mitigation;e-health security on could computing and its challenges;high speed multiplier using embedded approximate 4-2 compressor for image multiplication;a review on self-stabilizing platform in scope of merchant navy applications;study on information management system that connects students and instructor through chatting;machine learning approaches for microscopic image analysis and microbial object detection(MOD) as a decision support system;and literature survey on video surveillance crime activity recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on distribution inspection planning strategy based on artificial intelligence image recognition 24

Research on distribution inspection planning strategy based ...

引用

1st international conference on image processing machine learning and pattern recognition

作者： Gao, Fengxi Wu, Zhuohang Han, Zhentao Wang, Qixiang He, Xin Sun, Yan Zhao, Dewei Zhao, Wengang Sun, Mingze State Grid Liaoning Elect Power Compant Bcon Res Inst Shenyang Liaoning Peoples R China

ISBN: (纸本)9798400707032

In order to actively promote the construction of new power systems and the digital transformation and upgrading of power grid companies, and explore the application of artificial intelligence technology, the power grid company has built artificial intelligence "two libraries and one platform", that is, artificial intelligence platform, sample library, model library, and has carried out a lot of work in the application of artificial intelligence technology in equipment management, safe operation, marketing customer service and other business fields, and has precipitated rich samples, algorithms, and model achievements. With the increasing demand for intelligent application services and the increasing demand for samples and models in various business departments, it is urgent to introduce capabilities such as intelligent identification of electrical components and defect detection in scarce scenes on top of the existing artificial intelligence basic support capabilities to realize model training, iteration, optimization and improvement of accuracy, and deeply integrate the basic capabilities of artificial intelligence with the core business applications of the power grid. Further improve the ability to empower the profession and serve the grassroots.

关键词： New power systems Drone inspection Artificial intelligence Defect detection

来源：评论

学校读者我要写书评

暂无评论

Jewelry stones Classification: Case study 7

Jewelry Stones Classification: Case Study

引用

7th international conference of Soft Computing and pattern recognition (SoCPaR)

作者： Hurtik, Petr Vajgl, Marek Burda, Michal Univ Ostrava Ctr Excellence IT4Innovat Inst Res & Applicat Fuzzy Modeling 30 Dubna 22 CZ-70103 Ostrava 1 Czech Republic

ISBN: (纸本)9781467393607

The paper introduces a real-life industrial problem: a jewelry stones classification. The stones are represented by their camera images. The goal of the contract was to evaluate stones into two (or more) specified classes according to their quality. Given requirements include very high processing speed and success rate of the classification. The goal of this paper is to publish a report of this contract and show a way how this task can be solved. In this paper we aim to usage of machine learning with respect to the image processing. We also design own learning and classification algorithm and answer the question if there is a place for a new machine learning algorithm. As an output of this paper a benchmark of the proposed algorithm with 81 state-of-the-art machine learning methods is presented.

关键词： image classification machine learning image processing perceptron separation tree

来源：评论

学校读者我要写书评

暂无评论

A Methodology for Assessing Carbon Emission Indicators Based on Incorporates machine learning and Multi-modal data 24

A Methodology for Assessing Carbon Emission Indicators Based...

引用

1st international conference on image processing machine learning and pattern recognition

作者： Zhang, Shuang Liu, Jia Ma, Rui Sha, Jiangbo Kang, Wenni Qu, Fanghao Kang, Yibin Ningxia Elect Power Res Inst Yinchuan Ningxia Peoples R China State Grid Xintong Yili Technol Co Ltd Nanjing Peoples R China

ISBN: (纸本)9798400707032

Since the status of carbon emission indicators involves many factors, there is often a problem of large errors when evaluating them. For this reason, this paper proposes a study on a carbon emission indicator evaluation method that integrates machine learning and multi-modal data. After comprehensively analyzing the influencing factors of the value of carbon emission rights from the four perspectives of macroeconomics, energy prices, climate change, policy, and the international carbon market, we integrated multi-modal influencing factor data, calculated the corresponding carbon emission costs, and combined them as the input characteristic parameter of the BP neural network, through forward propagation and backward propagation, the linear relationship between it and the value of carbon emission rights is determined, and the corresponding model is constructed to realize the value evaluation of carbon emission rights. In the test results, the fit between the carbon emission rights value assessment results and the actual transaction price has always remained relatively stable, and the specific error has always been within 0.70 yuan/ton, with the maximum error being only 0.66 yuan/ton. Compared with the control group, it has obvious advantages in assessment accuracy and effectiveness respectively.

关键词： Fusion machine learning Multi-modal data Carbon emission indicators Carbon emission costs BP neural network Linear relationship

来源：评论

学校读者我要写书评

暂无评论

A Maximum or Minimum Way of Forming 2-D Histogram for image Optimal Multiple Value Segmentation 24

A Maximum or Minimum Way of Forming 2-D Histogram for Image ...

引用

1st international conference on image processing machine learning and pattern recognition

作者： Zhang, Yunfei Zhang, Zhan Xu, Ri Xiong, Ping Guangdong Univ Sci & Technol Coll Gen Educ Dongguan Peoples R China Aviat Planning & Design Inst Grp Co Ltd Integrate Planning Inst Marking Dept Beijing Peoples R China Avic Composite Corp Ltd Dept Planning & Dev Beijing Peoples R China

ISBN: (纸本)9798400707032

To resolve image multiple value segmentation difficulty, two novelty ways were putted forward in the light of the usually process to form 2-D entropy versus the traits of 2-D entropy in this text. In the first way, the 2-D histogram was defined as the central point's grey scale via maximum one of others 4 points in the same 4-neighborhood, In the second way, the 2-D histogram was defined as the central point's grey scale via minimum one of others 4 points in the same 4-neighborhood. Made a comparison with famous approach, test results of the first way on nearly whole of Matlab's images in image-processing toolbox that more details message about related targets in one image can be ideally kept, via test results of second way on introduced above images show that noise can be weakened better without losing any important outline message about related targets.

关键词： image multiple value segmentation 2-D entropy threshold

来源：评论

学校读者我要写书评

暂无评论

Effective Partitioning of Input Domains for ALM Algorithm

Effective Partitioning of Input Domains for ALM Algorithm

引用

1st Iranian conference on pattern recognition and image Analysis (PRIA)

作者： Afrakoti, Iman Esmaili Paeen Ghaffari, Aboozar Shouraki, Saeed Bagheri Sharif Univ Technol Dept Elect Engn Tehran Iran

ISBN: (纸本)9781467362061;9781467362047

This paper presents a new and simple algorithm for partitioning the input domain for implementation of Active learning Method (ALM) algorithm. ALM is a pattern-based algorithm for soft computing which uses the Ink Drop Spread (IDS) algorithm as its main engine for feature extraction. In this paper a simple algorithm is introduced with a few computation cost. In order to evaluate the performance of the proposed algorithm, it is applied to two applications, system modeling and pattern recognition. Simulation results show the effectiveness of our algorithm in specifying the appropriate points for dividing the inputs domains.

关键词： Active learning method (ALM) fuzzy inference algorithm ink drop spread (IDS)

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：