Proceedings of the 3rd International Conference on Machine Learning and Soft Computing最新文献_第4页

A Study on Machine Learning for Steganalysis 用于隐写分析的机器学习研究

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311000

K. Jung

引用次数: 12

Evaluation of the reference evapotranspiration for a greenhouse crop using an Adaptive-Network-Based Fuzzy Inference System (ANFIS) 基于自适应网络的模糊推理系统(ANFIS)评价温室作物参考蒸散量

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3310987

J. Balmat, F. Lafont, A. M. Ali, N. Pessel, J. C. R. Fernández

引用次数: 3

Towards data variation trends recommendation 对数据变化趋势提出建议

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311015

T. Nguyen, Phuc Quang Tran, H. T. Nguyen, Toan Phung Huynh, L. Hạnh, H. Huynh

引用次数: 0

Researches on the Security Protection and Inspection Method for Confidential Documents Based on Linux Operating System 基于Linux操作系统的机密文件安全保护与检查方法研究

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311029

Changqi Hu, Fei Chen, Hua Zheng

引用次数: 3

CNN and Traditional Classifiers Performance for Sign Language Recognition CNN和传统分类器在手语识别中的表现

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311011

Sobia Fayyaz, Y. Ayaz

{"title":"CNN and Traditional Classifiers Performance for Sign Language Recognition","authors":"Sobia Fayyaz, Y. Ayaz","doi":"10.1145/3310986.3311011","DOIUrl":"https://doi.org/10.1145/3310986.3311011","url":null,"abstract":"Many people around the world are suffering from vocal and hearing disabilities and they communicate with others by actions rather than speech. They prefer sign language (hand gestures) to convey what revolves in their mind. Every language has some set of rules of grammar to express information in meaningful way but not everyone can recognize what is being conveyed through sign language. Thus the automatic translation of a sign language serves as basic need for overcoming many difficulties and providing convenience for impaired people in the developing era of technology. For many years, a lot of researchers have been working on developing the better algorithm for sign language communication using machine learning and computer vision techniques that passes through many stages such as pre-processing, segmentation, extraction of features and classification. But the efficient features can produce more effective and accurate results. This paper aims at comparing performance of different classifiers to deep convolutional neural network (CNN) on sign language dataset providing with and without local feature descriptor and bag of visual words. This is definitely a classification task for which CNN, Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM) are being widely considered. CNN is capable of extracting and representing high-level abstractions in the dataset that results good accuracy but some traditional classifiers are also capable for that when providing with good features. We evaluate the performance of MLP and SVM without and with Speed up Robust Features (SURF) on the same data given to CNN. Results are also discussed in this paper that shows MLP and SVM employing descriptor gives high accuracy than CNN.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129652380","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: 2

Backbone solving algorithm based on heuristic thinking 基于启发式思维的主干求解算法

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3310989

Shaohua Guo, J. He, Xueting Song, Weiting Liu

{"title":"Backbone solving algorithm based on heuristic thinking","authors":"Shaohua Guo, J. He, Xueting Song, Weiting Liu","doi":"10.1145/3310986.3310989","DOIUrl":"https://doi.org/10.1145/3310986.3310989","url":null,"abstract":"In 1997, the definition of the backbone was proposed for the first time -- It was a set of variables that with invariant assignments in the solution of SAT problems. The scale of the backbone was closely related to the scale of the search in the SAT(Boolean Satisfiability Problem) problem, while it had important applications in fault diagnosis, stochastic 3-SAT problem and verification of the quality implication term, so that it was very important to solve the backbone at high speed. In 2010, J. Marques-Silva proposed one test per time algorithm, which greatly improved the computing efficiency of backbone. Based on the one test per time, this paper drew on the heuristic thinking, which designed the scoring mechanism and filtering strategy, also it had adjust the set to be tested. Based on this idea, this paper proposed the heuristic backbone algorithm, which could improve the speed of backbone solution. The test sample had used the benchmark standard test sample and the 2017 SAT competition test sample. The experimental results showed that compared with the one test per time algorithm, the solving time of the heuristic backbone algorithm had been significantly improved.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114800823","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

Clustering Stability via Concept-based Nonnegative Matrix Factorization 基于概念的非负矩阵分解聚类稳定性

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3310991

Nghia Duong-Trung, Minh Nguyen, Hanh T. H. Nguyen

{"title":"Clustering Stability via Concept-based Nonnegative Matrix Factorization","authors":"Nghia Duong-Trung, Minh Nguyen, Hanh T. H. Nguyen","doi":"10.1145/3310986.3310991","DOIUrl":"https://doi.org/10.1145/3310986.3310991","url":null,"abstract":"One of the most important contributions of topic modeling is to accurately and the ectively discover and classify documents in a collection of texts by a number of clusters/topics. However, finding an appropriate number of topics is a particularly challenging model selection question. In this context, we introduce a new unsupervised conceptual stability framework to access the validity of a clustering solution. We integrate the proposed framework into nonnegative matrix factorization (NMF) to guide the selection of desired number of topics. Our model provides a exible way to enhance the interpretation of NMF for the effective clustering solutions. The work presented in this paper crosses the bridge between stability-based validation of clustering solutions and NMF in the context of unsupervised learning. We perform a thorough evaluation of our approach over a wide range of real-world datasets and compare it to current state-of-the-art which are two NMF-based approaches and four Latent Dirichlet Allocation (LDA) based models. the quantitative experimental results show that integrating such conceptual stability analysis into NMF can lead to significant improvements in the document clustering and information retrieval the ectiveness.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122661294","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

MMSIA: Improved Max-Min Scheduling Algorithm for Load Balancing on Cloud Computing 改进的云计算负载均衡的Max-Min调度算法

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311017

Tran Cong Hung, Le Ngoc Hieu, Phan Thanh Hy, Nguyen Xuan Phi

{"title":"MMSIA: Improved Max-Min Scheduling Algorithm for Load Balancing on Cloud Computing","authors":"Tran Cong Hung, Le Ngoc Hieu, Phan Thanh Hy, Nguyen Xuan Phi","doi":"10.1145/3310986.3311017","DOIUrl":"https://doi.org/10.1145/3310986.3311017","url":null,"abstract":"Cloud computing is one of the most advanced technologies in information technology, a convergence of many achievements in research and development and application of new technologies. Cloud computing has also helped to reduce the cost of small and medium enterprises based on cloud provider services. As cloud computing evolves rapidly, researching optimizations such as task execution time, completion time, responce time, and virtual machine resources (VMs) are tremendous challenges. This article proposes an MMSIA algorithm to improve the Max-Min scheduling algorithm, which improves the completion time of the requests by using the \"learned learning\" machine learning, by clustering size of requests and clustering utilization percent of VMs. The algorithm then assigns the largest cluster requests to the VM with the least utilization percent, which is repeated when the request list is empty. In particular, the MMSIA algorithm has improved the completion time. The simulation results show that the proposed MMSIA algorithm has improved the completion time compared to the three algorithms: Max-Min, Min-Min and Roud Robin.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121051006","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: 19

Emotion Recognition by Integrating Eye Movement Analysis and Facial Expression Model 结合眼动分析和面部表情模型的情绪识别

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311001

V. Huynh, Hyung-Jeong Yang, Gueesang Lee, Soohyung Kim, In Seop Na

引用次数: 7

Evaluation Study of Unsupervised Face-to-Face Translation using Generative Adversarial Networks 基于生成对抗网络的无监督面对面翻译评价研究

Proceedings of the 3rd International Conference on Machine Learning and Soft Computing Pub Date : 2019-01-25 DOI: 10.1145/3310986.3311007

M. Iqbal, Risman Adnan, M. R. Widyanto, T. Basaruddin

引用次数: 0