检索结果-内蒙古大学图书馆

Information Systems and Computing Technology (ISCTech), International Conference on

作者： Shengjia Zhang Fuyuan Xiao School of Big Data and Software Engineering Chongqing University Chongqing China

Complex evidence theory (CET), which extends Dempster Shafer theory to a higher dimensional space, is well studied these days. In CET, how to generate CBBA is crucial for uncertainty reasoning, and it is still an open issue. To be specific, CBBA can be generated through data in real number field or in the complex number field. For the data in real number field, it is necessary to mapping it to complex number field. Meanwhile, it is better to reinforce features of data in the process of mapping. In this paper, a discrete Fourier transform-based feature reinforcement method is proposed to map the data from real number field to complex number field. What's more, we propose a novel reinforcement measurement, similarity indices, to quantify the level of the feature reinforcement. The experiments illustrate that the discrete Fourier transform-based feature reinforcement method achieves good performance, which can be beneficial to pattern recognition to some extent.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Gasoline RON Loss by Machine Learning 6

Predicting Gasoline RON Loss by Machine Learning

引用

6th IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2022

作者： Liu, Limin Chen, Zhen Wang, Yongsheng Liu, Guangwen Inner Mongolia University of Technology Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service College of Data Science and Application Hohhot China Inner Mongolia University of Technology College of Data Science and Application Hohhot China

ISBN: (数字)9781665469869

ISBN: (纸本)9781665469869

In order to improve gasoline quality and reduce the environmental pollution caused by gasoline combustion, we aim to study the nonlinear relationship between octane loss and various gasoline components in gasoline refining process, further optimize the gasoline refining process, and reduce the content of sulfur and olefin in gasoline products while minimizing the octane loss. Firstly, we used the nonlinear data reduction algorithm t-SNE to preprocess the data of each component in gasoline and clarify each characteristic parameter;then we constructed the Multiple Nonlinear Regression (MNR) model to analyze the correlation and influence of each characteristic data on octane value;finally, we selected NSGA-II multi-objective genetic algorithm. The NSGA-II multi-objective genetic algorithm was selected for in-depth optimization of the model. The multiple linear regression model was also constructed for comparison experiments, and the advantages and disadvantages of the predicted results of the two models were analyzed, as well as the feasibility of extension. In the experiments with industrial data samples published in Sinopec Gaoqiao Petrochemical real-time database (Honeywell PHD) and LIMS experimental database, it was found that the multivariate nonlinear regression model has more superiority in achieving the purpose of the study, the value of harmful content in gasoline was reduced by 32.7%, and the predicted data of each component of gasoline was more in line with environmental protection requirements. Therefore, the multivariate nonlinear model has the highest reasonableness in predicting the octane loss values. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The Investigation and Implementation of Automated Pricing and Replenishment Decisions for Vegetable Commodities Relying on Time Series Forecasting and Linear Programming Models

The Investigation and Implementation of Automated Pricing an...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Yi Tong Jinxuan Zhou Liang Deng Congao Zhang Tao Guo Xueling Long Department of Information Engineering Wuhan Business University Hubei China Major in Software Engineering Major in Data Science and Big DataTechnology Major in Internet of Things Engineering Major in Financial Management

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

In modern supermarkets, given the limited shelf life and the propensity for rapid declines in the sales of perishable goods, such as vegetables, it becomes imperative to conduct daily restocking based on historical sales and consumer demand to preclude the occurrence of undersold items the following day. Consequently, conducting restocking and pricing strategies based on sales and demand holds significant research importance for supermarkets. This study initially employs a multiple linear regression model to investigate the impact on profit by adjusting total sales (Q), sales price (P), and each component of cost-plus pricing (C, T, L, A), thereby determining the relationship between total sales and cost-plus pricing for each vegetable category, as well as the functional relationship between total sales and cost-plus pricing for each vegetable category. Based on the derived functional relationship, time series prediction and linear programming models are utilized to forecast the market demand for each vegetable category over a one-week period, subsequently formulating the daily restocking plan and pricing strategy for each vegetable category in the subsequent week to maximize supermarket profit while satisfying market demand. Finally, an analysis of saleable vegetable items reveals that 29 vegetable items can be displayed, with a total profit of 846.35 yuan. Upon testing the sales data of 300,000 vegetables, compared to the conventional display method sans the use of this model, the overall profit margin surged by 269.75 yuan, an increment of 47% relative to the initial profit, effectively enhancing the operational efficiency and profitability of the supermarket.

关键词： Profitability Time series analysis Linear regression Pricing Predictive models Linear programming data models Information technology Forecasting Testing

来源：评论

学校读者我要写书评

暂无评论

Belief Kullback-Leibler Divergence-based Dynamical Complexity Analysis for Biological Systems

Belief Kullback-Leibler Divergence-based Dynamical Complexit...

引用

Information Systems and Computing Technology (ISCTech), International Conference on

作者： Lang Zhang Fuyuan Xiao School of Big Data and Software Engineering Chongqing University Chongqing China

Physical states can be fed back by the physiological signal as it contains the information of healthy systems. Specifically, dynamical time series is valuable data to reflect the pathological states by means of measuring the complexity of time series. Nevertheless, how to measure the complexity of physical signal is still an open issue. In this paper, a novel complexity measurement algorithm based on belief Kullback-Leibler (KL) divergence, called BKLDC, is proposed to calculate the complexity of biological systems time series. BKLDC algorithm firstly truncates biological systems signal into several slices with boundaries. In this case, the interval and border values are taken into account, which can differentiate the time series data. Then, based on the Dempster-Shafer (D-S) evidence theory, the format of time series data is converted to basic probability assignments (BPA). So, the feature of time series is obtained effectively as BKLDC algorithm considers the uncertainty of data signal. Hence, the complexity of physiological signal can be obtained by figuring out the divergence of BPAs. The divergence reflects discrepancy of BPAs, which presents the inherent complexity of data to some extent. In addition, an implementation in cardiac interbeat interval time series demonstrates the out-performance of BKLDC algorithm for pathological states analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniMoCo: Unsupervised, Semi-Supervised and Fully-Supervised Visual Representation Learning

UniMoCo: Unsupervised, Semi-Supervised and Fully-Supervised ...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Cai, Bolun Chen, Junying South China University of Technology Key Lab. of Big Data & Intell. Robot MoE School of Software Engineering Guangzhou China Tencent Wechat Ai Guangzhou China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Momentum Contrast (MoCo) achieves great success for unsupervised visual representation learning. However, there are a lot of supervised and semi-supervised datasets, which are already labeled. To fully utilize the label annotations, we propose Unified Momentum Contrast (UniMoCo), which extends MoCo to support arbitrary ratios of labeled data and unlabeled data training. Compared with MoCo, UniMoCo has two modifications as follows: (1) Different from a single positive pair in MoCo, we maintain multiple positive pairs on-the-fly by comparing the query label to a label queue. (2) We propose a Unified Contrastive (UniCon) loss to support an arbitrary number of positives and negatives in a unified pair-wise optimization perspective. Our UniCon is more reasonable and powerful than the supervised contrastive loss in theory and practice. In our experiments, we pre-train multiple UniMoCo models with different ratios of ImageNet labels and evaluate the performance on various downstream tasks. Experiment results show that UniMoCo generalizes well for unsupervised, semi-supervised and fully-supervised visual representation learning. Besides, we surprisingly find that UniMoCo performs best with 60% ImageNet labels for COCO and VOC transfer learning. The code is available: https://***/dddzg/unimoco. © 2022 IEEE.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Dynamic Bi-Elman Attention Networks (DBEAN): Dual-Directional Context-Aware Representation Learning for Enhanced Text Classification

arXiv

引用

arXiv 2025年

作者： Liao, Mengyao Lai, Zhenglin Xu, Dong College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Text classification, a fundamental task in natural language processing (NLP), aims to categorize textual data into predefined labels. Traditional methods struggled with complex linguistic structures and semantic dependencies. The advent of deep learning, particularly recurrent neural networks (RNNs) and Transformer-based models, has significantly advanced the field by enabling nuanced feature extraction and context-aware predictions. Despite improvements, existing models exhibit limitations in balancing interpretability, computational efficiency, and long-range contextual understanding. This paper proposes the Dynamic Bidirectional Elman with Attention Network (DBEAN), which integrates bidirectional temporal modelling with self-attention mechanisms. DBEAN dynamically assigns weights to critical segments of input, improving contextual representation while maintaining computational efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Elman neural networks

来源：评论

学校读者我要写书评

暂无评论

Complex Belief KL Divergence in Complex Evidence Theory

Complex Belief KL Divergence in Complex Evidence Theory

引用

Information Systems and Computing Technology (ISCTech), International Conference on

作者： Junjie Huang Fuyuan Xiao School of Big Data and Software Engineering Chongqing University Chongqing China

A generalized Dempster-Shafer evidence theory, known as complex evidence theory can explain regularly fluctuating data and offer a better framework for uncertain information representing and processing. In this study, we propose a probabilistic transformation method to transform the complex basic belief assignments of complex evidence theory into probability distributions. Additionally, we propose a generalized Kullback-Leibler divergence to measure the discrepancy of two complex basic belief assignments. Besides, we prove the properties of the proposed divergence and validate its availability by numerical examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Light-Weight data Augmentation Method for Fault Localization

SSRN

引用

SSRN 2022年

作者： Hu, Jian Xie, Huan Lei, Yan Yu, Ke School of Big Data and Software Engineering Chongqing University Chongqing China

Context: Fault localization (FL) is essentially a search over the space of program statements to find suspicious entities that might have caused a program failure. However, the real-world programs are high dimensional and imbalanced, which limits the effectiveness and efficiency of existing FL methods. The state-of-the-art FL method (Aeneas) solves the imbalanced and high-dimensional problem but in a complex and time-consuming ***: Due to the limited effectiveness of original FL methods and the low efficiency of the state-of-the-art data augmentation method Aeneas, this paper proposes Lamont , a L ight-weight d a ta aug m entati on me t hod to improve the effectiveness of original FL methods and the efficiency of ***: Lamont uses revised linear discriminant analysis (LDA) to reduce the dimensionality of the original coverage matrix and leverage synthetic minority over-sampling (SMOTE) to generate the synthesized failing tests. The balanced coverage matrix with reduced dimensionality is fed into FL algorithms to obtain the ranked suspicious list of statements. To evaluate the efficiency and effectiveness, we compare Lamont with six representative FL methods and Aeneas on 458 versions of 10 real-life ***: It can be observed that Lamont outperforms in most cases for Top-K metric and reduces the number of statements that need to be checked from 17.45% to 79.81% compared with the original six FL methods. Furthermore, Lamont saves the time over the state-of-the-art data augmentation method Aeneas from 55.33% to 68.39% with comparable ***: This work conducts a large-scale experimental study to investigate the effectiveness and efficiency of Lamont . Two conclusions can be obtained based on the experimental results. First, it shows that Lamont is more effective than the original FL methods. Second, it shows Lamont is more efficient than Aeneas with similar effectiveness in six FL methods. © 2022, The Authors. All ri

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

CoSIL: software Issue Localization via LLM-Driven Code Repository Graph Searching

arXiv

引用

arXiv 2025年

作者： Jiang, Zhonghao Ren, Xiaoxue Yan, Meng Jiang, Wei Li, Yong Liu, Zhongxin The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China Ant Group Hangzhou China

Large language models (LLMs) have significantly advanced autonomous software engineering, leading to a growing number of software engineering agents that assist developers in automatic program repair. Issue localization forms the basis for accurate patch generation. However, because of limitations caused by the context window length of LLMs, existing issue localization methods face challenges in balancing concise yet effective contexts and adequately comprehensive search spaces. In this paper, we introduce CoSIL, an LLM-driven, simple yet powerful function-level issue localization method without training or indexing. CoSIL reduces the search space through module call graphs, iteratively searches the function call graph to obtain relevant contexts, and uses context pruning to control the search direction and manage contexts effectively. Importantly, the call graph is dynamically constructed by the LLM during search, eliminating the need for pre-parsing. Experiment results demonstrate that CoSIL achieves a Top-1 localization success rate of 43% and 44.6% on SWE-bench Lite and SWE-bench Verified, using Qwen2.5-Coder-32B, respectively, outperforming existing methods by 8.6%–98.2%. When CoSIL is applied to guide the patch generation stage, the resolved rate further improves by 9.3%–31.5%. Copyright © 2025, The Authors. All rights reserved.

关键词： Automatic programming

来源：评论

学校读者我要写书评

暂无评论

DDNet: Density and depth-aware network for object detection in foggy scenes

DDNet: Density and depth-aware network for object detection ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Boyi Xiao Jin Xie Jing Nie School of Big Data and Software Engineering Chongqing University Chongqing China School of Microelectronics and Communication Engineering Chongqing University Chongqing China

Fog causes serious degradation in image quality that in turn can degrade the performance of object detection. The main reason can be concluded that (i) the degraded images make object localization difficult, (ii) the difficulty in extracting robust features for accurate detection results in various fog densities. To address the above two problems, in this paper, we propose a simple yet efficient network named density and depth-aware network (DDNet), which consists of a density-aware attention network (DAANet) and a depth-aware non-local contextual network (DNCNet). The DNCNet captures long-range dependencies guided by depth information to improve object localization. DAANet employs an attention mechanism guided by predicted fog densities to ensure the robustness of features under different fog densities. Experiments are performed on the FoggyDriving dataset. Our approach achieves the state-of-the-art performance.

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：