检索结果-内蒙古大学图书馆

2023 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2023

作者： Yang, Biao Shi, Yuyi Wu, Zhaogang Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350336740

For the energy-saving scheduling problem of microwave heating titanium strip pickling flow shop, firstly, the microwave heating titanium strip pickling process is described as Flow Shop Scheduling Problem (FSSP), and the current energy-saving problems of the shop are analyzed. Secondly, a flow shop scheduling optimization model based on genetic algorithm is proposed for microwave heating titanium strip pickling, and brute force, Johnson, Nawaz-Enscore-Ham (NEH), and simulated annealing algorithms are used as comparison experiments. Finally, the experimental results show that after optimized scheduling, the scheduling scheme considering energy consumption reduces energy consumption by 14.6% compared with the scheduling scheme considering only the duration of work, which provides guidance for energy saving in enterprises. © 2023 IEEE.

关键词： Titanium

来源：评论

学校读者我要写书评

暂无评论

Data-free Binary Neural Network with Image Heterogeneity 16

Data-free Binary Neural Network with Image Heterogeneity

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Gu, Hongwei Duan, Yuxiu Shao, Zongkai Xiao, Pan Wang, Kaili Bai, Fenhua Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Unionscience Technology Group Co. Ltd Kunming China

ISBN: (纸本)9781510689251

Binary neural networks (BNNs) are widely used in image and video processing tasks because they can greatly reduce memory and accelerate inference speed to deploy in edge scenes. However, the deployment of BNN still faces the problem that the original data is not available. Data-free adversarial distillation (DFAD) focuses on solving model training problems in data-free scenarios. Therefore, combining BNN with DFAD provides a potential solution for lightweight model deployment in data-free scenarios. We introduce BNN into the DFAD framework for the first time, called Data-free binary neural network (DFBNN), but this combination faces challenges. Due to the information loss of BNN, the samples generated by the generator often lose category information, and the heterogeneity between categories is high, which leads to the decrease of learning performance of BNN student model. In order to cope with this challenge, we propose the category information entropy maximization loss to constrain the probability distribution of the samples generated in the same batch. In addition, the intra-class feature clustering constraint is proposed. By limiting the cosine distance of the same category features of the generated samples, the inter-class heterogeneity is ensured while focusing on solving the problem of low intra-class heterogeneity. A large number of experiments show that DFBNN is feasible and superior, and provides an effective solution for lightweight model deployment in data-free scenarios. © 2025 SPIE.

关键词： Binary data Quantization Neural networks Education and training Data modeling Ablation Convolution Network architectures Statistical modeling RGB color model

来源：评论

学校读者我要写书评

暂无评论

Phase Demodulation under Free Undersampling in Heterodyne Coherent Φ-OTDR 5

Phase Demodulation under Free Undersampling in Heterodyne Co...

引用

5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023

作者： Cui, Maojiang Li, Chuan Zhao, Zhengang Qian, Heng Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350336030

Heterodyne coherent detection phase-sensitive optical time-domain reflectometer (Φ-OTDR) is widely used in structural health monitoring of large facilities due to the ease of achieving stable phase demodulation, but it usually requires a high sampling rate. The sampling rate can be reduced effectively by undersampling, but the sampling rate of undersampling is strictly limited by spectrum aliasing effect. To solve this problem, this paper proposes a free undersampling phase demodulation method in the heterodyne coherent Φ-OTDR. The method changes from traditional 'distance' direction demodulation to 'time' direction demodulation of the recombination signal. Therefore, the spectrum aliasing in the 'distance' direction caused by undersampling does not affect the demodulation in the 'time' direction, and the sampling rate of undersampling can be freely selected. In the experiment, we proposed method can accurately demodulate the phase in sampling rates of 100 MSa/s and 10 MSa/s that within the sample rate restricted area of conventional undersampling demodulation method. © 2023 IEEE.

关键词： Demodulation

来源：评论

学校读者我要写书评

暂无评论

Continuous epoch distance integration for unsupervised person re-identification 5

Continuous epoch distance integration for unsupervised perso...

引用

5th International Conference on Communications, information System and Computer engineering, CISCE 2023

作者： Yang, Lei Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350326796

Unsupervised person re-identification aims to learn discriminative feature representations for person retrieval from unlabeled datasets. Clustering-based methods achieve state-of-the-art performance in this research direction. However, the noisy pseudo-labels generated during the clustering process and the interference caused by background noise limit the performance of the model. To this end, this paper proposes continuous epoch distance integration for unsupervised person re-identification, which performs clustering by integrating the distance matrix between two consecutive epochs to generate reliable pseudo-labels. In addition, the attention module of spatial structure and channel dimension is also proposed, so that the model pays more attention to the person itself and eliminates the interference of the background. The effectiveness of this method is verified on Market-1501, DukeMTMC-ReID, and MSMT17. The experimental results show that this method is superior to the current mainstream unsupervised person re-identification method. © 2023 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Thai-English Neural Machine Translation Method with Local and Global Syllable Feature 27

Thai-English Neural Machine Translation Method with Local an...

引用

27th International Conference on Asian Language Processing, IALP 2023

作者： Xiong, Ming Liu, Ruimin Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350330786

Neural Machine Translation (NMT) has superseded Statistical Machine Translation (SMT) owing to the advent of deep learning in natural language processing. However, enhancing the quality of low-resource NMT involves more nuanced strategies beyond data-dependent methods, especially for languages like Thai that lack substantial parallel corpus data for Thai-English translation. Addressing this problem, we introduce a Thai-English NMT methodology that amalgamates local and global syllabic features. Our approach employs a CNN-based module for extracting local syllable characteristics and capturing interdependencies among Thai syllable characters. Concurrently, a global syllable feature extraction mechanism is used to preserve sentence-level syllable traits. The integration of these features significantly augments Thai syllable context representation. In experiments conducted on the Thai-English corpus from the AL T dataset, our method improved the BLEU score by 2.11 points above the baseline, achieving a score of 12.99. This research holds potential implications for the translation of other syllable-based, low-resource languages, as well. © 2023 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor multiple extended objects tracking based on loopy sum-product algorithm 11

Multi-sensor multiple extended objects tracking based on loo...

引用

11th International Conference on information Systems and Computing technology, ISCTech 2023

作者： Li, Yuansheng Shen, Tao Wang, Qingwang Song, Jian Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350342406

A remarkable feature of extended objects (EOs), compared to the traditional point target, is that an EO normally produces more than one measurement, resulting in challenges for finding the associations among objects and measurements. In this paper, we are interested in tracking multiple EOs with multiple sensors by resorting to the loopy sum-product algorithm (LSPA). The marginal posterior of an EO state is approximately by belief, which is obtained by executing the LSPA on a suitably devised factor graph. The existence probability and belief of each EO are explicitly estimated, where the belief is modeled by mixture gamma Gaussian inverse Wishart (GGIW) distribution, so as to jointly estimate the measurement rate (MR), centroid state and extension. Simulation experiments verify the performance of the proposed method. © 2023 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Investigation to Screen Region Division for Stable Input of Eye-controlled Cursor

Investigation to Screen Region Division for Stable Input of ...

引用

2023 IEEE International Conference on Control, Electronics and Computer technology, ICCECT 2023

作者： Chen, Cheng Yin, Jibin Fu, Tiewei Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350399028

Aiming at the problems of stable cursor hovering and "Midas Touch"that are difficult to achieve in the current eye-controlled cursor technology, this paper has carried out an experimental study on the stable input of the eye-controlled cursor: Firstly, divide the screen into several small rectangular areas. When the eye-controlled cursor appears in any rectangular region, the position of the cursor will be fixed at the center of the rectangular region, and there will be no shaking of the eye-controlled cursor in a small range due to the natural wobble of the eyeball pupil. Then, the screen interface UI and icon sizes are adjusted according to the screen division level, to ensure that there is only one click target in each small rectangular area of the screen, and to ensure that there is no ambiguity when clicking on the eye-controlled cursor. Finally, by combining the task completion time, task completion rate, error rate, task difficulty, performance indicators, user satisfaction and other test data information to determine the most appropriate screen division size. © 2023 IEEE.

关键词： Touch screens

来源：评论

学校读者我要写书评

暂无评论

Positron Emission Tomography Lung Image Respiratory Motion Correcting with Equivariant Transformer

引用

Computers, Materials & Continua 2024年第5期79卷 3355-3372页

作者： Jianfeng He Haowei Ye Jie Ning Hui Zhou Bo She Faculty of Information Engineering and Automation Kunming University of Science and TechnologyYunnan Key Laboratory of Artificial IntelligenceKunming650500China School of Physics and Electronic Engineering Yuxi Normal UniversityYuxi653100China PET/CT Center Affiliated Hospital of Kunming University of Science and TechnologyFirst People’s Hospital of Yunnan ProvinceKunming650031China

In addressing the challenge of motion artifacts in Positron Emission Tomography (PET) lung scans, our studyintroduces the Triple Equivariant Motion Transformer (TEMT), an innovative, unsupervised, deep-learningbasedframework for efficient respiratory motion correction in PET imaging. Unlike traditional techniques,which segment PET data into bins throughout a respiratory cycle and often face issues such as inefficiency andoveremphasis on certain artifacts, TEMT employs Convolutional Neural Networks (CNNs) for effective featureextraction and motion ***’s unique approach involves transforming motion sequences into Liegroup domains to highlight fundamental motion patterns, coupled with employing competitive weighting forprecise target deformation field generation. Our empirical evaluations confirm TEMT’s superior performancein handling diverse PET lung datasets compared to existing image registration networks. Experimental resultsdemonstrate that TEMT achieved Dice indices of 91.40%, 85.41%, 79.78%, and 72.16% on simulated geometricphantom data, lung voxel phantom data, cardiopulmonary voxel phantom data, and clinical data, respectively. Tofacilitate further research and practical application, the TEMT framework, along with its implementation detailsand part of the simulation data, is made publicly accessible at https://***/yehaowei/temt.

关键词： PET lung scans respiratory motion correction triple equivariant motion transformer lie group motion decomposition

来源：评论

学校读者我要写书评

暂无评论

Feature selection of BOF steelmaking process data by using an improved grey wolf optimizer

引用

Journal of Iron and Steel Research International 2022年第8期29卷 1205-1223页

作者： Zong-xin Chen Hui Liu Long Qi Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500YunnanChina Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500YunnanChina

Basic oxygen furnace(BOF)steelmaking end-point control using soft measurement models has essential value for economy and ***,the high-dimensional and redundant data of the BOF collected by the sensors will hinder the performance of *** traditional feature selection results based on meta-heuristic algorithms cannot meet the stability of actual industrial *** order to eliminate the negative impact of feature selection application in the BOF steelmaking,an improved grey wolf optimizer(IGWO)for feature selection was proposed,and it was applied to the BOF data ***,the proposed algorithm preset the size of the feature subset based on the new encoding scheme,rather than the traditional uncertain number ***,opposition-based learning was used to initialize the grey wolf population so that the initial population was closer to the potential optimal *** addition,a novel population update method retained the features closely related to the best three grey wolves and probabilistically updated irrelevant features through measurement or random *** methods were used to search feature subsets to maximize search capability and stability of algorithm on BOF steelmaking ***,the proposed algorithm was compared with other feature selection algorithms on the BOF data *** results show that the proposed IGWO can stably select the feature subsets that are conductive to the end-point regression accuracy control of BOF temperature and carbon content,which can improve the performance of the BOF steelmaking.

关键词： Basic oxygen furnace Feature selection Grey wolf optimization Regression Opposition-based learning

来源：评论

学校读者我要写书评

暂无评论

Chinese Grammatical Error Correction via Large Language Model Guided Optimization Training 23rd

Chinese Grammatical Error Correction via Large Language Mod...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Liu, Xiao Li, Ying Yu, Zhengtao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Artificial Intelligence Kunming China

ISBN: (纸本)9789819783663

Pre-trained language model-based methods for Chinese Grammatical Error Correction (CGEC) are categorized into Seq2Seq and Seq2Edit types. However, both Seq2Seq and Seq2Edit models depend on high-quality training data significantly. Considering the strong generation and inference ability of large language models (LLMs), we propose a large language model-guided optimization training method to exploit LLMs to extract error knowledge to optimize the traditional CGEC model training process. On the one hand, we use error types and confusion sets as extra knowledge to guide LLMs to generate diverse pseudo data, thus extending the error distribution of our training data. On the other hand, LLMs are utilized to infer the predicted results from our CGEC models and obtain the re-training data, thus iteratively optimizing our pre-trained CGEC models. Experiments on two benchmark datasets show that our LLMs-guided optimization method with small-scale training data can achieve comparable results with baseline models with large-scale training data. Detailed comparison experiments demonstrate that both the early deviser pseudo data and the later re-training data are extremely useful for traditional CGEC model optimization training, and can benefit from each other. We will release our code and prompts at https://***/SakuraAcedia/llm-cgec-got to facilitate future work. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Error correction

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：