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

筛选
英文 中文
Empirical Comparison of Area under ROC curve (AUC) and Mathew Correlation Coefficient (MCC) for Evaluating Machine Learning Algorithms on Imbalanced Datasets for Binary Classification ROC曲线下面积(Area under ROC curve, AUC)和马修相关系数(Mathew Correlation Coefficient, MCC)在非平衡数据集上评估机器学习算法的经验比较
Chongomweru Halimu, Asem Kasem, S. Newaz
{"title":"Empirical Comparison of Area under ROC curve (AUC) and Mathew Correlation Coefficient (MCC) for Evaluating Machine Learning Algorithms on Imbalanced Datasets for Binary Classification","authors":"Chongomweru Halimu, Asem Kasem, S. Newaz","doi":"10.1145/3310986.3311023","DOIUrl":"https://doi.org/10.1145/3310986.3311023","url":null,"abstract":"A common challenge encountered when trying to perform classifications and comparing classifiers is selecting a suitable performance metric. This is particularly important when the data has class-imbalance problems. Area under the Receiver Operating Characteristic Curve (AUC) has been commonly used by the machine learning community in such situations, and recently researchers are starting to use Matthew Correlation Coefficient (MCC), especially in biomedical research. However, there is no empirical study that has been conducted to compare the suitability of the two metrics. In this paper, the aim of this study is to provide insights about how AUC and MCC are compared to each other when used with classical machine learning algorithms over a range of imbalanced datasets. In our study, we utilize an earlier-proposed criteria for comparing metrics based on the degree of consistency and degree of Discriminancy to compare AUC against MCC. We carry out experiments using four machine learning algorithms on 54 imbalanced datasets, with imbalance ratios ranging from 1% to 10%. The results demonstrate that both AUC and MCC are statistically consistent with each other; however AUC is more discriminating than MCC. The same observation is noticed when evaluated on 23 balanced datasets. This suggests AUC to be a better measure than MCC in evaluating and comparing classification algorithms.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"21 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":"117084428","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: 65
Face Reconstruction with Generative Adversarial Network 基于生成对抗网络的人脸重建
Dino Hariatma Putra, T. Basaruddin
{"title":"Face Reconstruction with Generative Adversarial Network","authors":"Dino Hariatma Putra, T. Basaruddin","doi":"10.1145/3310986.3311008","DOIUrl":"https://doi.org/10.1145/3310986.3311008","url":null,"abstract":"Generative Adversarial Network (GAN) is a framework of deep learning in generative models. The generative model aims to synthesize a new data so that it has a distribution of distribution according to the original data distribution. In the current development, GAN is not only used to synthesize data from noise alone, but in the current development it has begun to be used to translate data from a domain to data with a different domain. Several studies have been developed, such as CycleGAN, and Pix2pix. In this study, the face has not been used as an object of translation. In this study a model for translating images of face sketches into face images will be made.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"51 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":"115705604","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
Sliding Window Method on Quantum Key Distribution Protocol 量子密钥分发协议的滑动窗口方法
G. Mogos
{"title":"Sliding Window Method on Quantum Key Distribution Protocol","authors":"G. Mogos","doi":"10.1145/3310986.3311030","DOIUrl":"https://doi.org/10.1145/3310986.3311030","url":null,"abstract":"Two parties at a distance who wish to secretly communicate need a secret key to encrypt/decrypt the messages. To obtain the cryptographic key, the parties may agree on the cryptosystem to be used: symmetrical or asymmetrical. The aspect of symmetrical cryptosystems can be divided in two sub-aspects: encryption key distribution and use of an encryption method which is not vulnerable to attacks. This paper presents how we can use the classical method of Automatic Repeat Request-type to secure the procedure of encryption key distribution from Bechmann-Pasquinucci and Peres protocol. Consequently, for the transmission through the physical communication environment, the data are encapsulated in a frame by adding a header and a piece of control information.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"47 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":"125839589","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
Solving Dietary Planning Problem using Particle Swarm Optimization with Genetic Operators 基于遗传算子的粒子群算法求解膳食规划问题
Edmarlyn Porras, Arnel C. Fajardo, Ruji P. Medina
{"title":"Solving Dietary Planning Problem using Particle Swarm Optimization with Genetic Operators","authors":"Edmarlyn Porras, Arnel C. Fajardo, Ruji P. Medina","doi":"10.1145/3310986.3311005","DOIUrl":"https://doi.org/10.1145/3310986.3311005","url":null,"abstract":"Dietary planning problem is considered as Multi-dimensional Knapsack Problem and confirmed to be a NP-hard problem. There are different ways on how to generate a dietary plan and it includes different constraints such as having a variety of foods, meeting the required total calories, satisfying different nutrients and others. Particle swarm optimization is a promising method to solve different kinds of optimization problem due to its fast convergence, few parameters needed and ability to find good solutions to the problem. PSO using constriction coefficient method was applied in this study and genetic operators were integrated to explore the search space and improved the quality of the solution. Experimental results show that the proposed algorithm was able to generate a varied diet plans for adults wherein it satisfies the specified constraints and PSO with genetic operators was able to evolve better solutions compare to original PSO.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"8 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":"122209405","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: 5
QASA: Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations QASA:基于学习对问题感知的自关注文档表示进行排序的开放域问答高级文档检索器
Trang M. Nguyen, Van-Lien Tran, Duy-Cat Can, Quang-Thuy Ha, L. T. Vu, Chng Eng Siong
{"title":"QASA: Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations","authors":"Trang M. Nguyen, Van-Lien Tran, Duy-Cat Can, Quang-Thuy Ha, L. T. Vu, Chng Eng Siong","doi":"10.1145/3310986.3310999","DOIUrl":"https://doi.org/10.1145/3310986.3310999","url":null,"abstract":"For information consumers, being able to obtain a short and accurate answer for a query is one of the most desirable features. This motivation, along with the rise of deep learning, has led to a boom in open-domain Question Answering (QA) research. While the problem of machine comprehension has received multiple success with the help of large training corpora and the emergence of attention mechanism, the development of document retrieval in open-domain QA is lagged behind. In this work, we propose a novel encoding method for learning question-aware self-attentive document representations. By applying pair-wise ranking approach to these encodings, we build a Document Retriever, called QASA, which is then integrated with a machine reader to form a complete open-domain QA system. Our system is thoroughly evaluated using QUASAR-T dataset and shows surpassing results compared to other state-of-the-art methods.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"19 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":"131421577","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
Image-Based Silkworm Egg Classification and Counting Using Counting Neural Network 基于图像的计数神经网络蚕卵分类与计数
Supachaya Prathan, S. Auephanwiriyakul, N. Theera-Umpon, S. Marukatat
{"title":"Image-Based Silkworm Egg Classification and Counting Using Counting Neural Network","authors":"Supachaya Prathan, S. Auephanwiriyakul, N. Theera-Umpon, S. Marukatat","doi":"10.1145/3310986.3310988","DOIUrl":"https://doi.org/10.1145/3310986.3310988","url":null,"abstract":"Silkworm egg classification and counting are essential tasks in the silkworm industry for promotion and conservation of the silkworm gene. Normally, the egg counting process is done by human or estimated from the average weight of an egg. However, these methods have been proven to be both time-consuming and inaccurate. Therefore, in this work, we develop a silkworm counting system that can count eggs laid on the disease-free laying (DFL) sheet image. The system can count eggs in all classes that are in the fresh, all-blue, and shell period. The result shows that the system yields approximately 80 to 88% counting rate in fresh and shell period. Whereas in the all-blue period, the system can produce about 60 to 78% counting rate because of the condition of the type of DFL sheet and the similar characteristic of all-blue in the early stage and unfertilized eggs.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"31 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":"125292031","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
Exploring the Relationship between the Structural and the Actual Similarities of Automata 探讨自动机的结构相似度与实际相似度之间的关系
P. Grachev, R. Bezborodov, I. Smetannikov, A. Filchenkov
{"title":"Exploring the Relationship between the Structural and the Actual Similarities of Automata","authors":"P. Grachev, R. Bezborodov, I. Smetannikov, A. Filchenkov","doi":"10.1145/3310986.3311032","DOIUrl":"https://doi.org/10.1145/3310986.3311032","url":null,"abstract":"One of the most common representations of formal languages is deterministic finite-state automata. In recent years, a bunch of papers dedicated to the problem of synthesizing such an automaton by a list of positive and negative examples of some formal language was published. Many of proposed models try to construct candidate automaton, which is believed to somehow approximate the target one. In this paper, we exploring the relationship between the structural similarity of candidate and target finite-state automata and the percentage of common words in their formal languages. We formalize two different notions of automata similarity, and present the results of their comparison and draw conclusions regarding the applicability of these definitions to the problem of grammar inference.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"1 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":"129809615","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
Improved collaborative filtering recommendations using quantitative implication rules mining in implication field 在蕴涵领域改进了基于定量蕴涵规则挖掘的协同过滤推荐
H. T. Nguyen, H. Huynh, Lan Phuong Phan, H. Huynh
{"title":"Improved collaborative filtering recommendations using quantitative implication rules mining in implication field","authors":"H. T. Nguyen, H. Huynh, Lan Phuong Phan, H. Huynh","doi":"10.1145/3310986.3310996","DOIUrl":"https://doi.org/10.1145/3310986.3310996","url":null,"abstract":"Collaborative filtering recommendation based on association rule mining has become a research trend in the field of recommender systems. However, most research results only focus on binary data, whereas in practice sets of transactions are usually quantitative data. Moreover, association rule mining algorithms are designed to focus on optimizing for basket analysis, so that in order to better serve for recommendation, they need to be adjusted. Therefore, a solution for recommender systems to deal with association rules on both binary and quantitative data as well as improve the quality of recommendation based on the rule set is a challenge today. This paper proposes a new approach to improve the accuracy, the performance and the time of recommendation by the model based on quantitative implication rules mining in the implication field.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"6 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":"116742733","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
Self-developed Three Wheels Omni-Directional for Autonomous Mobile Robots 自主研制的三轮全方位自主移动机器人
Truong Le Phuong, Khai La Khai
{"title":"Self-developed Three Wheels Omni-Directional for Autonomous Mobile Robots","authors":"Truong Le Phuong, Khai La Khai","doi":"10.1145/3310986.3310995","DOIUrl":"https://doi.org/10.1145/3310986.3310995","url":null,"abstract":"The proposed system presents the method to self-developed three wheels Omni-directional for autonomous mobile robots. The implementation system including 60W Planet DC motor for three wheels, three encoders for speed feedback, one encoder for distance feedback, one digital compass sensor for angle feedback. The hardware system includes two section, the first one is the main system it received the signal from sensor compass and encoder and then it controls three subsystems to adjust steering speed each wheel. The second one is the sub-system with the mission control only one DC motor from the control signal of the main system. The main system is developed based STM32F407 and the sub-system is an STM32F103 microcontroller. Furthermore, The PID algorithm is applied to control speed DC motor and the trajectory generation algorithms have been built for Omni-directional. From the implementation results, the proposed system yields good quality trajectories and implementable real-time. The error of positional is 1.33% and the angle is 1.75%.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"18 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":"125655416","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
Inception-v3-Based Recommender System for Crops 基于inception -v3的作物推荐系统
E. P. Guidang
{"title":"Inception-v3-Based Recommender System for Crops","authors":"E. P. Guidang","doi":"10.1145/3310986.3310993","DOIUrl":"https://doi.org/10.1145/3310986.3310993","url":null,"abstract":"Inception-v3 model is an image classifier that is commonly used in predictive modelling using an image as an input. Specifically, it achieved the following objectives a) Identify the major crops grown in the Philippines; b) Identify the soil requirements of crops; c) Classify Soil Texture images using Inception-v3; and d) Develop precision crop framing procedure based on Inception-v3. A threshold was set to 60%. The label having highest score that passes the preset threshold was used as a basis in the recommender system. The Inception-v3 model recognizes very well the images are that are clear and recognizable. Inception-v3 is an excellent tool in developing an image-based recommender system. However, the big challenge for authors who are also planning to do similar system lies on how to train the inception-v3 moel without over or under fitting. What can be done to solve thi issue is to play or manipulate the learning rate and the number of epochs. These are said to be the deterministic parameters to fine tune the model.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"11 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":"115906819","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信