2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)最新文献_第4页

A novel Adam approach related to Decoupled Weight Decay (AdamL) 一种与解耦权衰减(AdamL)相关的新型Adam方法

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769816

Ricardo Xavier Llugsi Cañar, S. El Yacoubi, Allyx Fontaine, P. Lupera

{"title":"A novel Adam approach related to Decoupled Weight Decay (AdamL)","authors":"Ricardo Xavier Llugsi Cañar, S. El Yacoubi, Allyx Fontaine, P. Lupera","doi":"10.1109/LA-CCI48322.2021.9769816","DOIUrl":"https://doi.org/10.1109/LA-CCI48322.2021.9769816","url":null,"abstract":"The use of optimizers makes it possible to reduce losses during the learning process of a neural network. Currently there are some types of optimizers whose effectiveness has already been proven, an example of this is Adam. Adam is an extension to Stochastic Gradient Decent that makes use of Momentum and Adaptive Learning to converge faster. An interesting alternative to complement the Adam’s work is the addition of weight decay. This is done to decouple the weight decay from the gradient-based update. Some attempts have been developed previously, however its correct operation has not been keenly proven. In this work, a weight decay decoupling alternative is presented and acutely analyzed. The algorithm’s convergence is mathematically verified and its operation too through the use of a Convolutional Encoder-Decoder network and the application of strategies for error reduction. The AdamL operation is verified by the achievement of a proper Temperature Forecast with a percentage error lower than 4.5%. It can be seen too that the forecast error deepens around noon but it does not exceed 1.47°C.","PeriodicalId":431041,"journal":{"name":"2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparison of Feature Extraction Methods for Brazilian Legal Documents Clustering 巴西法律文件聚类特征提取方法比较

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769839

João Pedro Lima, J. A. F. Costa, Diógenes Carlos Araújo

{"title":"Comparison of Feature Extraction Methods for Brazilian Legal Documents Clustering","authors":"João Pedro Lima, J. A. F. Costa, Diógenes Carlos Araújo","doi":"10.1109/LA-CCI48322.2021.9769839","DOIUrl":"https://doi.org/10.1109/LA-CCI48322.2021.9769839","url":null,"abstract":"This article aims to evaluate the impact of different textual feature extraction methods in the task of clustering Brazilian legal texts. We compared Binary Bag of Words, Bag of Words, Term Frequency-Inverse Document Frequency, Word2vec and Doc2vec models in different dimensions and with different hyperparameters, totaling 45 models. Our experiment consists in evaluating the result of clustering done by K-Means algorithm over the vectors created by each model. The evaluation was done both quantitatively, using clustering evaluation metrics, and qualitatively, considering relevant aspects for the application of this type of algorithm in the legal environment, such as transparency and interpretability. Our experiments were conducted in a database of 30,000 documents in Brazilian Portuguese of judicial moves of the Tribunal de Justiça do Rio Grande do Norte (TJRN). The research results suggest that the TF-IDF method seems to be the most suitable for the task, outperforming the other models in considered metrics. The other methods appear to perform equally well, with the exception of Doc2vec, which performed poorly.","PeriodicalId":431041,"journal":{"name":"2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128827819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Towards explainable artificial intelligence for the leukemia subtype recognition 面向白血病亚型识别的可解释人工智能

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769826

R. Ochoa-Montiel, Gustavo Olague, Juan Humberto Sossa Azuela

引用次数: 0

Feature Vector Design for Music Genre Classification 音乐类型分类的特征向量设计

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769848

Víctor Muñiz, J. B. O. S. Filho, Souza Filho

引用次数: 2

Deep Learning on Automatic Fall Detection 基于深度学习的自动跌倒检测

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769783

Sara Monteiro, Argentina Leite, E. J. S. Pires

引用次数: 0

Machine learning techniques versus complexity theory in the cerebral haemodynamics of traumatic brain injury patients 机器学习技术与复杂性理论在外伤性脑损伤患者脑血流动力学中的比较

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769819

María Fernanda Lobos Vásquez, Roberth Alcivar-Cevallos, R. Panerai, M. Chacón

{"title":"Machine learning techniques versus complexity theory in the cerebral haemodynamics of traumatic brain injury patients","authors":"María Fernanda Lobos Vásquez, Roberth Alcivar-Cevallos, R. Panerai, M. Chacón","doi":"10.1109/LA-CCI48322.2021.9769819","DOIUrl":"https://doi.org/10.1109/LA-CCI48322.2021.9769819","url":null,"abstract":"The objective of this study was to compare two paradigms of haemodynamic signals analysis which have been used to characterize between two physiological states. Cerebral blood flow velocity and arterial blood pressure signals of 30 patients with traumatic brain injury (TBI) and 30 healthy subjects were obtained non-invasively. Although different machine learning models have been tested with successful results in many cases of clinical interest, there is emerging evidence that complexity and entropy analysis of biomedical signals can detect underlying changes in physiology which relates to diseases. In many studies, both paradigms have been proved in high accuracy in discriminating between health and disease. In this current work a SVM model and two Complexity-Entropy planes were developed, achieving great power in discriminating health from TBI patients, with an AUC of 0.89 for the machine learning approach, and a highest 0.94 AUC by one of the Complexity-Entropy planes. There are almost no cases that compare these two paradigms, which makes it of great interest to put them side by side and discuss their contributions and particularities.","PeriodicalId":431041,"journal":{"name":"2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114215779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic expansion to improve diversity in query formulation 语义扩展，提高查询公式的多样性

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769853

Elliot Ide, C. Olivares-Rodríguez

{"title":"Semantic expansion to improve diversity in query formulation","authors":"Elliot Ide, C. Olivares-Rodríguez","doi":"10.1109/LA-CCI48322.2021.9769853","DOIUrl":"https://doi.org/10.1109/LA-CCI48322.2021.9769853","url":null,"abstract":"Although the diversity of results has been studied since the early information retrieval systems, few studies explore diversity and its representation in an educational context. Inherently, approaches that seek to address difficulties in web search are focused on maximizing the relevance of results over the original query. This work presents a method that integrates semantic relationships using Word Embedding for expansion with blind feedback to improve diversity. Using a corpus based on the user’s query logs from a realistic setting, three Word2vec models are trained to obtain semantically relevant terms for each naturally elaborated query by students. The proposed architecture is studied in a specific search task, limiting the number of candidate terms in each model according to the allowed frequency of words. Finally, the diversity in two groups of queries is compared, measuring the lexical similarity of the snippets of the results pre-expansion and post-expansion. Results indicate the potential for improving diversity, also showing that lower semantic similarity can lead to better diversity. Therefore, we provide a method to improve learning through web searches.","PeriodicalId":431041,"journal":{"name":"2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129725765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evolutionary latent space search for driving human portrait generation 驱动人类肖像生成的进化潜在空间搜索

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.48550/arXiv.2204.11887

Benjamín Machín, S. Nesmachnow, J. Toutouh

引用次数: 8

Development of a computer platform for the enrichment of cultural environments using VR and AR 开发虚拟现实、增强现实丰富文化环境的计算机平台

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769849

K. Medrano, Rene Tejada, B. González

引用次数: 0

Subset Feature Selection with Structural Variables 基于结构变量的子集特征选择

2021 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Pub Date : 2021-11-02 DOI: 10.1109/LA-CCI48322.2021.9769843

J. A. Urrutia, P. Estévez, J. Vergara

引用次数: 0