检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

606 篇 会议

馆藏范围

606 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

396 篇 工学
- 376 篇 计算机科学与技术...
- 323 篇 软件工程
- 85 篇 信息与通信工程
- 67 篇 控制科学与工程
- 64 篇 安全科学与工程
- 55 篇 交通运输工程
- 35 篇 生物工程
- 28 篇 生物医学工程（可授...
- 15 篇 光学工程
- 15 篇 电气工程
- 14 篇 仪器科学与技术
- 14 篇 化学工程与技术
- 12 篇 机械工程
- 12 篇 电子科学与技术（可...
- 10 篇 动力工程及工程热...
128 篇 理学
- 71 篇 数学
- 40 篇 生物学
- 40 篇 统计学（可授理学、...
- 30 篇 系统科学
- 19 篇 物理学
- 12 篇 化学
113 篇 管理学
- 85 篇 管理科学与工程(可...
- 80 篇 图书情报与档案管...
- 24 篇 工商管理
39 篇 医学
- 36 篇 基础医学(可授医学...
- 35 篇 临床医学
- 26 篇 公共卫生与预防医...
- 14 篇 药学(可授医学、理...
14 篇 农学
- 13 篇 作物学
12 篇 法学
11 篇 经济学
- 11 篇 应用经济学
6 篇 教育学

主题

152 篇 machine learning
75 篇 adversarial mach...
61 篇 accuracy
55 篇 machine learning...
42 篇 computational mo...
40 篇 deep learning
39 篇 predictive model...
33 篇 data models
29 篇 training
28 篇 federated learni...
27 篇 support vector m...
24 篇 feature extracti...
24 篇 convolutional ne...
22 篇 real-time system...
21 篇 prediction algor...
15 篇 analytical model...
15 篇 security
14 篇 signal processin...
14 篇 optimization
13 篇 random forests

机构

10 篇 faculty of compu...
7 篇 sri lanka instit...
5 篇 university of co...
4 篇 sri lanka instit...
4 篇 department of in...
3 篇 sri lanka instit...
3 篇 maharashtra pune
3 篇 telangana hydera...
3 篇 southwest jiaoto...
3 篇 department of so...
3 篇 sri lanka instit...
3 篇 faculty of gradu...
3 篇 school of comput...
3 篇 department of el...
3 篇 vishwakarma inst...
3 篇 artificial intel...
3 篇 hyderabad
3 篇 nanjing universi...
3 篇 faculty of compu...
3 篇 key laboratory o...

作者

9 篇 samadhi rathnaya...
6 篇 rathnayake samad...
4 篇 thusithanjana th...
4 篇 subba rao s.p.v.
3 篇 thilakarthna thu...
3 篇 shaik subhani
3 篇 fernando harinda
3 篇 ramaswamy t.
3 篇 ghazali rozaida
3 篇 hassim yana mazw...
3 篇 harinda fernando
3 篇 dharrao deepak
2 篇 pham tuan anh
2 篇 chowdhury jamim ...
2 篇 samantha mathara...
2 篇 muhammad ehsan r...
2 篇 rana muhammad eh...
2 篇 ahire aaditya
2 篇 reddad hakima
2 篇 lim kit guan

语言

514 篇 英文
92 篇 其他
7 篇 中文

检索条件"任意字段=6th Asia Conference on Machine Learning and Computing, ACMLC 2024"

共 606 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

acmlc 2024 - 2024 6th asia conference on machine learning and computing

ACMLC 2024 - 2024 6th Asia Conference on Machine Learning an...

引用

6th asia conference on machine learning and computing, acmlc 2024

ISBN: (纸本)9798400710018

the proceedings contain 29 papers. the topics discussed include: forecasting of photovoltaic power using deep learning;investigating the factors affecting risky levels of alcohol consumption among students using machine learning approach;a study of relationship between business performance and stock prices using machine learning techniques;anomaly and pattern detection using advanced machine learning models;machine learning regression model development and data visualization of road accident in Urdaneta City, Pangasinan, Philippines;deep learning-driven sentiment analysis: unlocking insights in topic-specific twitter conversations;tour itinerary planner: a genetic algorithm and clustering approach for travel plan and hotel recommendation;and enhancing fraud prevention: exploring the interplay of internal control system, organizational culture, internal audit roles and online whistleblowing mechanisms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly and Pattern Detection Using Advanced machine learning Models 24

Anomaly and Pattern Detection Using Advanced Machine Learnin...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Nacchanandana, Piyavachara Suleiman, Basem Anaissi, Ali Picones, Gio School of Computer Science and Engineering University of New South Wales Sydney Australia University of Sydney Sydney Australia

ISBN: (纸本)9798400710018

this research addresses a unique intersection in the field of machine learning: the convergence of anomaly detection and decentralized learning. Although each domain has been extensively studied in isolation, their combination remains relatively unexplored. this study pioneers in investigating the practicality and efficiency of decentralized anomaly detection. We achieve this by integrating the GANomaly architecture with Federated learning, a novel approach that allows us to analyze the impact of various factors on system performance. the core of our investigation revolves around four aggregation methods: Federated Averaging, FedProx, Federated Personalization, and the newly introduced Federated Median. We meticulously evaluate the efficacy of these methods within a combined GANomaly and Federated learning framework, focusing on their performance across different levels of local computation and varying proportions of straggler clients per round. this research not only fills a gap in the existing literature, but also offers new insights into the optimization of decentralized learning systems for effective anomaly detection. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Generalized Posterior Calibration via Sequential Monte Carlo Sampler 24

Generalized Posterior Calibration via Sequential Monte Carlo...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Tanaka, Masahiro Faculty of Economics Fukuoka University Fukuoka Fukuoka Japan

ISBN: (纸本)9798400710018

As the amount and complexity of available data increases, the need for robust statistical learning becomes more pressing. To enhance resilience against model misspecification, the generalized posterior inference method adjusts the likelihood term by exponentiating it with a learning rate, thereby fine-tuning the dispersion of the posterior distribution. this study proposes a computationally efficient strategy for selecting an appropriate learning rate. the proposed approach builds upon the generalized posterior calibration (GPC) algorithm, which is designed to select a learning rate that ensures nominal frequentist coverage. this algorithm, which evaluates the coverage probability using bootstrap samples, has high computational costs because of the repeated posterior simulations needed for bootstrap samples. To address this limitation, the study proposes an algorithm that combines elements of the GPC algorithm with the sequential Monte Carlo (SMC) sampler. By leveraging the similarity between the learning rate in generalized posterior inference and the inverse temperature in SMC sampling, the proposed algorithm efficiently calibrates the posterior distribution with a reduced computational cost. For demonstration, the proposed algorithm was applied to several statistical learning models and shown to be significantly faster than the original GPC. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Forecasting of photovoltaic power using deep learning 24

Forecasting of photovoltaic power using deep learning

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Lertwiputh, Akarapon Watcharopas, Chakrit Wattuya, Pakaket Department of Computer Science Faculty of Science Kasetsart University Bangkok Thailand

ISBN: (纸本)9798400710018

the forecasting of photovoltaic (PV) power presents a solution to mitigate the impact of fluctuations in PV power, thereby enhancing grid stability and reducing the overall impact on power generation planning. Consequently, this facilitates the integration of more PV generation into the grid, contributing to an increase in electricity generation from renewable energy sources. this study employs deep learning algorithms as the primary technique to forecast PV power, with a forecast horizon extending up to 10 days ahead. the findings suggest that the Multilayer Perceptron is the preferred technique for constructing a forecast model using numerical weather prediction data, while a model incorporating Convolutional Neural Networks and Long Short-Term Memory is well-suited for implementing with sequences of historical data. Additionally, we assess the performance of the models by evaluating the Root Mean Square Error for PV power forecasting validation. © 2024 Copyright held by the owner/author(s).

关键词： PV power forecasting

来源：评论

学校读者我要写书评

暂无评论

DeltaAug: Cross-Modal Hard Feature Mining for Few-Shot learning 24

DeltaAug: Cross-Modal Hard Feature Mining for Few-Shot Learn...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Chen, Xuan School of Management Science and Engineering Central University of Finance and Economics Beijing China

ISBN: (纸本)9798400710018

Few-shot learning, i.e., learning quickly from only a few examples, is of significant practical value within the realm of artificial intelligence. the challenges of this task are primarily associated with the issue of overfitting. Despite promising attempts, previous efforts still yield unsatisfactory results in indistinguishable categories. To address this, we propose DeltaAug, an innovative Cross-Modal hard feature mining strategy that leverages arithmetic operations of multi-modal features in pre-trained CLIP to significantly expand the dataset size. We first analyze the multi-modal characteristics of hard classes in pre-trained CLIP, deducing an automatic discovery of hard categories prone to confusion. Following this, we develop a novel approach for uni-and cross-modality feature augmentation in the well-aligned visual-textual distribution of CLIP. the augmented features increase the amount of information available for supervised training and improve the distinctiveness of the extracted features, resulting in a superior performance with limited training data. Experimental results on eleven datasets demonstrate the robustness and outstanding classification performance of the proposed method in response to limited training data. © 2024 Copyright held by the owner/author(s).

关键词： few-shot learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-Driven Sentiment Analysis: Unlocking Insights in Topic-Specific Twitter Conversations 24

Deep Learning-Driven Sentiment Analysis: Unlocking Insights ...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Taggu, Amar Dubey, Chetana Paul, Rosy Department of Computer Science and Engineering North Eastern Regional Institute of Science and Technology Nirjuli India

ISBN: (纸本)9798400710018

the current work introduces an advanced deep learning (DL) approach to perform sentiment analysis on Twitter, focusing on topic-specific contexts. Traditional sentiment analysis models often fall short in accurately interpreting the diverse and context-sensitive nature of social media language. the proposed approach utilizes cutting-edge neural network architectures, including convolutional neural networks (CNNs) and bidirectional long short-term memory networks (BiLSTMs), to effectively capture the complex linguistic patterns and sentiment nuances within tweets. By incorporating topic modeling techniques, the model's ability to discern sentiment in relation to specific subjects is enhanced. Extensive experiments using a variety of datasets demonstrate that this method significantly outperforms existing baseline models in terms of accuracy and robustness. Use of deep learning yields better accuracy in both topic detection (96% (DL) vs 86% [6] vs 82% (basline)) and sentiment analysis (87%(DL) vs 82% [3] vs 76% (basline)). the results suggest that this deep learning-based approach not only improves sentiment classification but also offers valuable insights into public opinion on various topics. © 2024 Copyright held by the owner/author(s).

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

A study of relationship between business performance and stock prices using machine learning techniques 24

A study of relationship between business performance and sto...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Rukpanichsiri, Vorapat Soonthornphisaj, Nuanwan Department of Computer Science Faculty of Science Kasetsart University Bangkok Thailand

ISBN: (纸本)9798400710018

this research investigates the relationship between fundamental factors and stock prices. the study uses 50 stocks listed on the SET100 index in 2022. the fundamental factors of interest are earnings per share (EPS), price-to-book value (P/BV), net profit margin, dividend yield, return on assets (ROA), return on equity (ROE), and debt-to-equity ratio (D/E). the study uses quarterly data for 10 years, from 2012 to 2021. this results in 40 data points per stock. the relationship between fundamental factors and stock prices is investigated using machine learning methods, including Lasso, Regression Tree, Random Forest, AdaBoost, Xgboost, Gradient Boosting, and Neural Network. the relationship between fundamental factors and stock prices is evaluated using k-fold cross-validation. this method divides the data into training and testing sets. the performance of each model is measured using the R-squared value. the findings of the study suggest that some fundamental factors are significant predictors of stock prices. the strongest relationships are found in P/BV. the results also suggest that Neural Network methods can be used to identify the relationships between fundamental factors and stock prices. © 2024 Copyright held by the owner/author(s).

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Enhancing Data Labeling through Integration of SS-DBSCAN Clustering and Human-in-the-Loop 24

Enhancing Data Labeling Through Integration of SS-DBSCAN Clu...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Monko, Gloriana J. Kimura, Masaomi Department of Functional Control Systems Shibaura Institute of Technology Tokyo Japan School of Engineering Shibaura Institute of Technology Koto City Tokyo Japan

ISBN: (纸本)9798400710018

this study introduces a novel method for integrating Stratified Sampling for Density-Based Spatial Clustering of Applications with Noise (SS-DBSCAN) clustering with the human-in-the-loop approach to semi-supervised data labeling. We enhance the feature representation of text data using attention mechanisms, leading to the formation of more contextually relevant clusters. the clusters are then processed using SS-DBSCAN, where a custom similarity function aligns them closely with expert-labeled examples, facilitating efficient label propagation. Subsequently, human experts reevaluate the clustering outputs, refining the process by reassessing the feature similarities to the expert-labeled classes. this iterative process ensures high fidelity in label assignment and enhances the overall reliability of the semi-supervised learning approach. Applied to MIMIC III and Cancer Doc Classification datasets, this method not only aligns the data labels more closely with expert evaluations but also leverages human judgment to confirm the accuracy and reliability of the re-clustering process. Based on the BERT transformers model, the fine-tuned prediction model achieved 100% accuracy in predicting the correct label and evaluated the re-clustering technique's effectiveness, demonstrating 90.3% and 97.8% correctness in the re-clustered labels in MIMIC III and Cancer Doc Classification datasets, respectively. © 2024 Copyright held by the owner/author(s).

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning for Joint Entity and Relation Extraction on Open-domain 24

Multi-task Learning for Joint Entity and Relation Extraction...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Tian, Jiayue Kimura, Masaomi Graduate School Shibaura Institute of Technology Koto City Tokyo Japan Graduate School Shibaura Institute of Technology Tokyo Japan

ISBN: (纸本)9798400710018

Joint entity and relation extraction is a critical task in natural language processing, aimed at extracting structured triples from texts. this process is essential for building knowledge bases that support applications like semantic search and content analysis. Named Entity Recognition (NER) is often utilized in relation extraction (RE) as a separate stage in traditional methods or as one of the training targets in modern deep learning methods. In this paper, we propose a multi-task learning approach for RE that integrates NER as one of the training targets while fine-tuning a pre-trained Transformer-based language model (LM). Building on previous work, we utilized an intermediate product of the Transformer's attention mechanism, to represent specific NER tags in a sentence. the shared layers in the Transformer capture features for both RE and NER, resulting in more robust and generalized features that enhance our model's RE performance. We tested our approach on two popular open-domain RE datasets, the New York Times (NYT) and the WebNLG, using four NER types: location, organization, person, and country. the results show that our model achieved state-of-the-art performance of F1 score on both datasets, outperforming several span-level RE baseline models. Further analysis showed that our model demonstrated superior performance in Single Entity Overlap, a challenging scenario in RE. these findings demonstrate the effectiveness of our multi-task learning approach in improving joint entity and relation extraction. © 2024 Copyright held by the owner/author(s).

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Investigating the Factors Affecting Risky Levels of Alcohol Consumption among Students Using machine learning Approach 24

Investigating the Factors Affecting Risky Levels of Alcohol ...

引用

6th asia conference on machine learning and computing, acmlc 2024

作者： Shanchary, Sara Fariha Meraz, Md Naved Hakim, Ayman Ibne Faiyaz, Chowdhury Nafis Oshman, Muhammad Shafayat Department of Electrical and Computer Engineering North South University Dhaka Bangladesh

ISBN: (纸本)9798400710018

Addressing the pressing issue of alcohol consumption among students is crucial for the well-being of young individuals and the community. Understanding and mitigating alcohol related challenges faced by young people is essential for their healthy development. this study utilizes machine learning models to analyze data from a Portuguese school, aiming to link students' alcohol consumption levels to personal and familial factors. the primary objective is to identify key factors associated with high alcohol consumption among students. After data preprocessing on their dataset, we employed various machine learning algorithms, including hyperparameter-optimized Decision Tree, Random Forest, Boosting, and Ensemble learning. Our findings revealed that the decision tree algorithm performed well in predicting risky alcohol consumption for our target research question. Our selected feature subset showed strong positive correlation with the target variable, achieving an accuracy of 80.9 percent on the test set and 98.43 percent on the train set. Notably, this project breaks new ground by using explainable artificial intelligence to add reason to our prediction based on students' familial relationships, expanding upon previous research that also focused on demographic factors. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共61页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：